CN102004548B - System and method of inputting information by using image collecting equipment - Google Patents
System and method of inputting information by using image collecting equipmentDownload PDFInfo
- Publication number
- CN102004548B CN102004548BCN 201010550092CN201010550092ACN102004548BCN 102004548 BCN102004548 BCN 102004548BCN 201010550092CN201010550092CN 201010550092CN 201010550092 ACN201010550092 ACN 201010550092ACN 102004548 BCN102004548 BCN 102004548B
- Authority
- CN
- China
- Prior art keywords
- motion vector
- motion
- information
- input
- effective
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese【技术领域】【Technical field】
本发明涉及信息输入领域，特别是关于利用图像采集设备进行信息输入的系统及其方法。The invention relates to the field of information input, in particular to a system and method for information input using an image acquisition device.
【背景技术】【Background technique】
现有的电子设备，以手机为例，进行信息输入的方式一种是键盘输入方式，另外一种是触摸屏输入方式。由于触摸屏输入方式符合人们的书写习惯，因此逐渐成为输入方式的主流。In existing electronic devices, taking a mobile phone as an example, one way of inputting information is a keyboard input way, and the other is a touch screen input way. Since the touch screen input method conforms to people's writing habits, it gradually becomes the mainstream of the input method.
但现有的手写板和触摸屏，由于成本问题难以普及。而现有的手机中通常都包含摄像头，如果能利用摄像头代替手写板或者触摸屏来进行信息的输入则能够在很多地方提供便捷的输入。But existing tablet and touch screen are difficult to popularize because of cost problem. And generally all comprise camera in existing mobile phone, if can utilize camera to replace tablet or touch screen to carry out the input of information then can provide convenient input in many places.
【发明内容】【Content of invention】
本发明的目的在于提供一种利用图像采集设备进行信息输入的方法。The purpose of the present invention is to provide a method for information input using an image acquisition device.
本发明的另一目的在于提供一种利用图像采集设备进行信息输入的系统。Another object of the present invention is to provide a system for information input using an image acquisition device.
为达成前述目的，本发明一种利用图像采集设备进行信息输入的方法；其包括：In order to achieve the aforementioned purpose, the present invention provides a method for information input using an image acquisition device; it includes:
对图像进行分块获取每个分块的运动矢量；The image is divided into blocks to obtain the motion vector of each block;
对获取的运动矢量进行长度滤波；Perform length filtering on the obtained motion vector;
获取图像运动的主要运动矢量；Obtain the main motion vector of the image motion;
对主要运动矢量进行时间去噪，获取有效的运动矢量；Perform time denoising on the main motion vectors to obtain effective motion vectors;
对所述有效运动矢量进行信息的译码获取其具体表征的输入信息。Information decoding is performed on the effective motion vector to obtain input information specifically represented by it.
进一步地，在进行输入信息检测之前还包括首先定义输入信息的起始和终止时间段的步骤。Further, before detecting the input information, it also includes the step of firstly defining the start and end time periods of the input information.
进一步地，所述对获取的运动矢量进行长度滤波包括：设定运动矢量阀值，小于运动矢量阀值的运动矢量判断为扰动，滤除判断为扰动的运动矢量。Further, the length filtering of the obtained motion vectors includes: setting a motion vector threshold, judging motion vectors smaller than the motion vector threshold as disturbances, and filtering out motion vectors judged as disturbances.
进一步地，所述获取图像运动的主要运动矢量包括：对长度滤波后的运动矢量的方向建立直方图，横轴表征方向，纵轴表征该方向运动矢量的个数；获取直方图的峰值，该峰值的方向表示当前图像中目标运动的方向，该方向的运动矢量为主要运动矢量。Further, the acquisition of the main motion vector of the image motion includes: establishing a histogram for the direction of the length-filtered motion vector, the horizontal axis represents the direction, and the vertical axis represents the number of motion vectors in this direction; obtaining the peak value of the histogram, the The direction of the peak indicates the direction of the target motion in the current image, and the motion vector in this direction is the main motion vector.
进一步地，所述对主要运动矢量进行时间去噪，获取有效的运动矢量包括：设定运动矢量的时间阀值，连续存在时间小于时间阀值的运动矢量判断为扰动，连续存在时间大于所述时间阀值的运动矢量的运动方向为有效运动方向。Further, the time denoising the main motion vectors and obtaining effective motion vectors includes: setting a time threshold of the motion vector, and judging a motion vector whose continuous existence time is less than the time threshold as a disturbance, and whose continuous existence time is longer than the time threshold The motion direction of the motion vector of the time threshold is the effective motion direction.
进一步地，对所述有效运动矢量进行信息的译码包括：通过调取信息表征存储单元存储的输入信息和运动矢量的对应关系确定运动矢量具体表征的输入信息。Further, decoding the information of the effective motion vector includes: determining the input information specifically represented by the motion vector by calling the corresponding relationship between the input information stored in the information representation storage unit and the motion vector.
进一步地，如果输入时间段内有多个有效运动矢量，对多个有效运动矢量按时间顺序排列形成有效运动矢量组合，前述信息表征存储单元存储的为输入信息和运动矢量组合的对应关系。Further, if there are multiple valid motion vectors within the input time period, the multiple valid motion vectors are arranged in time order to form a valid motion vector combination, and the aforementioned information represents the corresponding relationship between the input information and the motion vector combination stored in the storage unit.
为达成前述另一目的，本发明一种利用图像采集设备进行信息输入的系统，其包括：In order to achieve the aforementioned another purpose, the present invention provides a system for information input using an image acquisition device, which includes:
运动估计单元，其用于对图像中分块进行运动搜索获取运动矢量；A motion estimation unit, which is used to perform a motion search on the block in the image to obtain a motion vector;
长度滤波单元，用于对运动估计单元获取的运动矢量进行长度滤波排除扰动；A length filtering unit, configured to perform length filtering on the motion vector obtained by the motion estimation unit to remove disturbances;
主要运动矢量计算单元，用于计算当前图像的运动目标的主要运动矢量；The main motion vector calculation unit is used to calculate the main motion vector of the moving object in the current image;
时间滤波单元，用于对所述主要运动矢量进行时间上的去噪，最终获取有效的运动矢量；A temporal filtering unit, configured to perform temporal denoising on the main motion vector, and finally obtain an effective motion vector;
运动矢量译码单元，用于对所述有效运动矢量进行信息译码获取其具体表征的输入信息。The motion vector decoding unit is configured to perform information decoding on the effective motion vector to obtain input information specifically represented by it.
进一步地，所述系统还包括输入片断确定单元，用于定义输入信息的起始和终止时间段。Further, the system further includes an input segment determination unit, configured to define the start and end time periods of the input information.
进一步地，长度滤波单元设定运动矢量阀值，小于运动矢量阀值的运动矢量判断为扰动，滤除判断为扰动的运动矢量。Further, the length filtering unit sets a motion vector threshold, and the motion vectors smaller than the motion vector threshold are judged as disturbances, and the motion vectors judged as disturbances are filtered out.
进一步地，主要运动矢量计算单元对长度滤波单元长度滤波后的运动矢量的方向建立直方图，横轴表征方向，纵轴表征该方向运动矢量的个数；然后获取直方图的峰值，该峰值的方向表示当前图像中目标运动的方向，该方向的运动矢量为主要运动矢量。Further, the main motion vector calculation unit establishes a histogram for the direction of the motion vector filtered by the length filter unit, the horizontal axis represents the direction, and the vertical axis represents the number of motion vectors in this direction; then obtain the peak value of the histogram, the peak value of the peak value Direction indicates the direction of target motion in the current image, and the motion vector in this direction is the main motion vector.
进一步地，所述时间滤波单元设定运动矢量的时间阀值，连续存在时间小于时间阀值的运动矢量判断为扰动，连续存在时间大于所述时间阀值的运动矢量的运动方向为有效运动方向。Further, the time filtering unit sets the time threshold of the motion vector, the motion vector whose continuous existence time is less than the time threshold is judged as a disturbance, and the motion direction of the motion vector whose continuous existence time is greater than the time threshold is the effective motion direction .
进一步地，所述运动矢量译码单元还包括一个存储运动矢量和对应信息表征的存储单元，通过调取信息表征存储单元存储的输入信息和运动矢量的对应关系确定运动矢量具体表征的输入信息。Further, the motion vector decoding unit further includes a storage unit for storing the motion vector and the corresponding information representation, and the input information specifically represented by the motion vector is determined by calling the corresponding relationship between the input information stored in the information representation storage unit and the motion vector.
所述系统进一步包括一个有效组合单元，当输入时间段内有多个有效运动矢量时，所述有效组合单元对多个有效运动矢量按时间顺序排列形成有效运动矢量组合，前述信息表征存储单元存储的为输入信息和运动矢量组合的对应关系。The system further includes an effective combination unit. When there are multiple effective motion vectors in the input time period, the effective combination unit arranges the multiple effective motion vectors in chronological order to form an effective motion vector combination. The aforementioned information represents the storage unit. is the corresponding relationship between input information and motion vector combination.
本发明的利用图像采集设备进行信息输入的系统及其方法，利用图像采集设备采集运动图像，并对图像进行分块，分别获取每一分块的运动矢量，然后对运动矢量进行长度滤波、获取主运动矢量以及进行时间滤波获取有效运动矢量，再利用预先存储的运动矢量与输入信息的对应关系获得运动矢量表示的输入信息，从而实现利用图像采集设备即可实现信息的输入，可以代替手写板或触摸屏实现信息输入，能够降低产品成本。The system and method for information input using an image acquisition device of the present invention use the image acquisition device to collect moving images, divide the images into blocks, obtain the motion vectors of each block respectively, and then perform length filtering on the motion vectors to obtain The main motion vector and time filtering are used to obtain the effective motion vector, and then the corresponding relationship between the pre-stored motion vector and the input information is used to obtain the input information represented by the motion vector, so that the information input can be realized by using the image acquisition device, which can replace the handwriting board Or the touch screen realizes information input, which can reduce product cost.
【附图说明】【Description of drawings】
图1是利用图像采集设备进行信息输入的方法的流程示意图。FIG. 1 is a schematic flowchart of a method for information input using an image acquisition device.
图2是利用图像采集设备进行信息输入的系统的结构框图。Fig. 2 is a structural block diagram of a system for information input using an image acquisition device.
【具体实施方式】【Detailed ways】
此处所称的“一个实施例”或“实施例”是指可包含于本发明至少一个实现方式中的特定特征、结构或特性。在本说明书中不同地方出现的“在一个实施例中”并非均指同一个实施例，也不是单独的或选择性的与其他实施例互相排斥的实施例。此外，表示一个或多个实施例的方法、流程图或功能框图中的单元顺序并非固定的指代任何特定顺序，也不构成对本发明的限制。Reference herein to "one embodiment" or "an embodiment" refers to a particular feature, structure or characteristic that can be included in at least one implementation of the present invention. "In one embodiment" appearing in different places in this specification does not all refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments. Furthermore, the order of elements in a method, flowchart, or functional block diagram representing one or more embodiments does not necessarily refer to any particular order nor constitute a limitation of the present invention.
本发明是关于向电子设备，例如手机、PDA或平板电脑等进行信息输入的系统和方法，其中这些电子设备中均配备有图像采集设备，例如摄像头。下面将以手机为例，以向手机内输入中文汉字信息为具体实例对本发明的系统和方方进行说明。The present invention relates to a system and method for inputting information to electronic devices, such as mobile phones, PDAs or tablet computers, etc., wherein these electronic devices are all equipped with image acquisition devices, such as cameras. The system and method of the present invention will be described below by taking the mobile phone as an example and inputting Chinese character information into the mobile phone as a specific example.
因为有的汉字可能只有一个笔画，而有的汉字笔画比较多，对于多笔画的汉字可以将汉字拆解成不同笔画进行输入信息检测，然后将各笔画组合成一个完整的汉字。单笔画的汉字作为多笔画汉字的一个特例。下面以输入的信息为多个笔画的汉字为例对本发明的信息输入系统和方法进行说明。Because some Chinese characters may have only one stroke, while some Chinese characters have more strokes. For Chinese characters with multiple strokes, the Chinese characters can be disassembled into different strokes for input information detection, and then each stroke can be combined into a complete Chinese character. Single-stroke Chinese characters are a special case of multi-stroke Chinese characters. The information input system and method of the present invention will be described below by taking Chinese characters whose input information is a plurality of strokes as an example.
请参阅图1所示，其显示本发明的利用摄像头进行信息输入的方法的流程图，其中输入的信息为多笔画的汉字。如图1所示，本发明的利用摄像头进行信息输入的方法其包括：Please refer to FIG. 1 , which shows a flow chart of the method of using a camera for information input of the present invention, wherein the input information is Chinese characters with multiple strokes. As shown in Figure 1, the method for information input using a camera of the present invention comprises:
步骤S11：在向手机内输入信息时，首先需要定义一次进行输入信息检测的输入时间，也可以称为定义输入片断，在输入片断内进行输入信息的检测。在定义输入片断时可以是设定某个按键按下到弹起的时间，也可以是直接定义一次输入的时间。在输入片断定义的时间内完成的输入才是一个输入信息，如果定义的输入时间片断还未结束，则可以继续输入笔画，在输入片断定义的时间结束之后才进行输入信息的最终判断。Step S11: When inputting information into the mobile phone, it is first necessary to define an input time for detecting the input information, which can also be called as defining an input segment, in which the input information is detected. When defining an input segment, it can be to set the time from when a button is pressed to when it is popped up, or to directly define the time for an input. The input that is completed within the time defined by the input segment is an input message. If the defined input time segment has not ended, you can continue to input strokes, and the final judgment of the input information will be made after the time defined by the input segment ends.
步骤S12：在输入片断内，摄像头采集输入的图像，例如是通过手指运动进行汉字的书写，则摄像头采集手指运动的图像，对图像进行分块进行运动估计，获取每一个分块的运动矢量。关于视频图像中运动检测的技术可以采用现有的各种运动检测的方法，例如帧间差分法、背景相减法、统计平均法、中值滤波器法等等，关于运动检测的方法的具体原理及内容本说明书不再一一列举详细说明。Step S12: In the input segment, the camera collects the input image, such as writing Chinese characters through finger movement, then the camera collects the image of the finger movement, performs motion estimation on the image blocks, and obtains the motion vector of each block. The technology of motion detection in video images can use various existing motion detection methods, such as inter-frame difference method, background subtraction method, statistical average method, median filter method, etc., the specific principle of the method of motion detection And content This instruction manual will not enumerate in detail one by one.
步骤S13：对获取的运动矢量进行长度滤波。因为在输入过程中可能有时候是操作者并未进行输入动作，而是一些扰动因素被摄像头捕捉到，例如手指的弯曲或者抖动等其他小动作。为避免这些扰动因素对输入信息的干扰，可以设置一个运动矢量长度的阀值，当运动矢量的长度大于该长度阀值时才认为是操作者在进行信息输入，如果运动矢量的长度小于该长度阀值，则认为该运动矢量是扰动，滤除该运动矢量。Step S13: Perform length filtering on the acquired motion vector. Because during the input process, sometimes the operator does not perform the input action, but some disturbance factors are captured by the camera, such as bending or shaking of fingers and other small actions. In order to avoid these disturbing factors from interfering with the input information, a threshold value of the motion vector length can be set. When the length of the motion vector is greater than the length threshold, it is considered that the operator is inputting information. If the length of the motion vector is smaller than the length threshold, the motion vector is considered to be a disturbance, and the motion vector is filtered out.
步骤S14：获取图像运动的主要运动矢量。对经过长度滤波之后的运动矢量的方向建立直方图，横轴表征方向，纵轴表征该方向运动矢量的个数；获取直方图的峰值，该峰值的方向表示当前图像中目标运动的方向，该方向的运动矢量为主要运动矢量。Step S14: Obtain the main motion vectors of the image motion. Establish a histogram for the direction of the motion vector after length filtering, the horizontal axis represents the direction, and the vertical axis represents the number of motion vectors in this direction; obtain the peak value of the histogram, and the direction of the peak represents the direction of the target motion in the current image. The motion vector in the direction is the principal motion vector.
步骤S15：对主要运动矢量进行时间去噪，获取有效的运动矢量。因为有些运动矢量虽然长度满足长度的阀值，但有可能是操作者的误操作，比如手指从摄像头前偶然的滑动，可能运动矢量也很长。为确定确实是操作者在输入信息，可以设定运动矢量的存在时间阀值，当运动矢量的存在时间小于该预定的时间阀值时，判断该运动矢量为扰动，对其进行滤波去除，当运动矢量的连续存在时间超过该预定的时间阀值时判断该运动矢量的运动方向为有效运动方向，该运动矢量为有效运动矢量。Step S15: Perform temporal denoising on the main motion vectors to obtain effective motion vectors. Because although the length of some motion vectors meets the length threshold, it may be a misoperation by the operator, such as a finger accidentally sliding from the front of the camera, and the motion vector may also be very long. In order to confirm that the operator is indeed inputting information, the existence time threshold of the motion vector can be set. When the existence time of the motion vector is less than the predetermined time threshold, it is judged that the motion vector is a disturbance, and it is filtered to remove it. When the continuous existence time of the motion vector exceeds the predetermined time threshold, it is judged that the motion direction of the motion vector is an effective motion direction, and the motion vector is an effective motion vector.
步骤S16：对各有效运动矢量进行组合。因为每一笔画对应一个运动矢量，为表示整个汉字，需要对各有效运动矢量进行组合，例如对多个有效运动矢量按时间顺序排列形成有效运动矢量组合。Step S16: Combine the effective motion vectors. Because each stroke corresponds to a motion vector, in order to represent the whole Chinese character, each effective motion vector needs to be combined, for example, a plurality of effective motion vectors are arranged in chronological order to form an effective motion vector combination.
步骤S17：对输入的有效运动矢量组合进行译码。可以提前预先设定输入信息(例如汉字输入的笔画)与运动矢量组合的对应关系，在对运动矢量组合进行译码时，通过调取预先存储的输入信息和运动矢量组合的对应关系确定运动矢量组合具体表征的输入信息。Step S17: Decode the input effective motion vector combination. The corresponding relationship between input information (such as Chinese character input strokes) and the combination of motion vectors can be preset in advance, and the motion vector can be determined by calling the corresponding relationship between the pre-stored input information and the combination of motion vectors when decoding the combination of motion vectors Combining input information for concrete representations.
对于单笔画的汉字的输入可以将运动矢量组合的步骤看作是单个笔画自己的组合，也可以理解为不需要进行运动矢量组合，相应地，预先设定的输入信息是与运动矢量的对应关系，在对运动矢量进行译码时，通过调取预先存储的输入信息和运动矢量的对应关系确定运动矢量具体表征的输入信息。For the input of single-stroke Chinese characters, the step of motion vector combination can be regarded as the combination of a single stroke itself, and it can also be understood that no motion vector combination is required. Correspondingly, the preset input information is the corresponding relationship with the motion vector , when decoding the motion vector, the input information specifically represented by the motion vector is determined by calling the correspondence between the pre-stored input information and the motion vector.
请参阅图2所示，其显示本发明的利用图像采集设备进行信息输入的系统1的一个实施例的结构框图。如图2所示，本发明的利用图像采集设备进行信息输入的系统1其包括运动估计单元11、长度滤波单元12、主要运动矢量计算单元13、时间滤波单元14、有效组合单元15以及组合译码单元16。Please refer to FIG. 2 , which shows a structural block diagram of an embodiment of a system 1 for information input using an image acquisition device according to the present invention. As shown in FIG. 2 , the system 1 for information input using an image acquisition device of the present invention includes a motion estimation unit 11, a length filter unit 12, a main motion vector calculation unit 13, a time filter unit 14, an effective combination unit 15, and a combination translator. Code unit 16.
运动估计单元11，其用于对图像中分块进行运动搜索获取运动矢量。在一个实施例中，例如是通过手指运动进行汉字的书写，则摄像头采集手指运动的图像，运动估计单元11对图像进行分块进行运动估计，获取每一个分块的运动矢量。关于视频图像中运动检测的技术可以采用现有的各种运动检测的方法，例如帧间差分法、背景相减法、统计平均法、中值滤波器法等等，关于运动检测的方法的具体原理及内容本说明书不再一一列举详细说明。The motion estimation unit 11 is used for performing motion search on blocks in the image to obtain motion vectors. In one embodiment, for example, if finger movement is used to write Chinese characters, the camera collects images of finger movement, and the motion estimation unit 11 performs motion estimation on the image blocks to obtain a motion vector of each block. The technology of motion detection in video images can use various existing motion detection methods, such as inter-frame difference method, background subtraction method, statistical average method, median filter method, etc., the specific principle of the method of motion detection And content This instruction manual will not enumerate in detail one by one.
长度滤波单元12，用于对运动估计单元11获取的运动矢量进行长度滤波排除扰动。因为在输入过程中可能有时候是操作者并未进行输入动作，而是一些扰动因素被摄像头捕捉到，例如手指的弯曲或者抖动等其他小动作。为避免这些扰动因素对输入信息的干扰，可以设置一个运动矢量长度的阀值，当运动矢量的长度大于该长度阀值时才认为是操作者在进行信息输入，如果运动矢量的长度小于该长度阀值，则认为该运动矢量是扰动，滤除该运动矢量。The length filtering unit 12 is configured to perform length filtering on the motion vector acquired by the motion estimation unit 11 to remove disturbances. Because during the input process, sometimes the operator does not perform the input action, but some disturbance factors are captured by the camera, such as bending or shaking of fingers and other small actions. In order to avoid these disturbing factors from interfering with the input information, a threshold value of the motion vector length can be set. When the length of the motion vector is greater than the length threshold, it is considered that the operator is inputting information. If the length of the motion vector is smaller than the length threshold, the motion vector is considered to be a disturbance, and the motion vector is filtered out.
主要运动矢量计算单元13，用于计算当前图像的运动目标的主要运动矢量。主要运动矢量计算单元13对经过长度滤波单元12长度滤波之后的运动矢量的方向建立直方图，横轴表征方向，纵轴表征该方向运动矢量的个数；然后获取直方图的峰值，该峰值的方向就表示当前图像中目标运动的方向，该方向的运动矢量为主要运动矢量。The main motion vector calculation unit 13 is used to calculate the main motion vector of the moving object in the current image. The main motion vector calculation unit 13 establishes a histogram for the direction of the motion vector after length filtering by the length filter unit 12, the horizontal axis represents the direction, and the vertical axis represents the number of motion vectors in this direction; then obtain the peak value of the histogram, the peak value of the peak value Direction indicates the direction of target motion in the current image, and the motion vector in this direction is the main motion vector.
时间滤波单元14，用于对所述主要运动矢量计算单元13计算出的主要运动矢量进行时间上的去噪，最终获取有效的运动矢量。因为有些运动矢量虽然长度满足长度的阀值，但有可能是操作者的误操作，比如手指从摄像头前偶然的滑动，可能运动矢量也很长。为确定确实是操作者在输入信息，可以设定运动矢量的存在时间阀值，当运动矢量的存在时间小于该预定的时间阀值时，判断该运动矢量为扰动，对其进行滤波去除，当运动矢量的连续存在时间超过该预定的时间阀值时判断该运动矢量的运动方向为有效运动方向，该运动矢量为有效运动矢量。The temporal filtering unit 14 is configured to perform temporal denoising on the main motion vectors calculated by the main motion vector calculation unit 13, and finally obtain effective motion vectors. Because although the length of some motion vectors meets the length threshold, it may be a misoperation by the operator, such as a finger accidentally sliding from the front of the camera, and the motion vector may also be very long. In order to confirm that the operator is indeed inputting information, the existence time threshold of the motion vector can be set. When the existence time of the motion vector is less than the predetermined time threshold, it is judged that the motion vector is a disturbance, and it is filtered to remove it. When the continuous existence time of the motion vector exceeds the predetermined time threshold, it is judged that the motion direction of the motion vector is an effective motion direction, and the motion vector is an effective motion vector.
有效组合单元15，在本实施例中输入信息是多笔画的汉字输入，每一个笔画对应一个有效运动矢量，当输入时间段内有多个有效运动矢量时，所述有效组合单元15对多个有效运动矢量按时间顺序排列形成有效运动矢量组合。Effective combination unit 15, in the present embodiment, input information is the Chinese character input of multiple strokes, and each stroke corresponds to an effective motion vector, when there are multiple effective motion vectors in the input time period, described effective combination unit 15 is to a plurality of The valid motion vectors are arranged in time order to form a valid motion vector combination.
组合译码单元16用于对前述有效组合单元15组合后的有效运动矢量组合进行译码，获取其具体表征的输入信息。在组合译码单元16内包括一个存储运动矢量组合和对应信息表征的存储单元161，在译码时，组合译码单元16调取存储单元161内储存的运动矢量和对应信息表征的对应关系，则可以获取该运动矢量组合具体表征的输入信息。The combined decoding unit 16 is configured to decode the effective motion vector combination combined by the aforementioned effective combination unit 15 to obtain input information specifically represented by it. In the combination decoding unit 16, a storage unit 161 is included to store the motion vector combination and the corresponding information representation. When decoding, the combination decoding unit 16 calls the corresponding relationship between the motion vector stored in the storage unit 161 and the corresponding information representation, Then the input information specifically represented by the motion vector combination can be obtained.
在前述实施例中是包含有效组合单元，将多笔画组合成一个汉字，如果是单笔画汉字，可以看作是有效组合单元的特例，只对一个笔画进行组合或者理解为不需要该有效组合单元。In the foregoing embodiment, an effective combination unit is included to combine multiple strokes into a Chinese character. If it is a single-stroke Chinese character, it can be regarded as a special case of an effective combination unit, and only one stroke is combined or understood as not requiring the effective combination unit. .
在本发明的实施例中，其还可以包括一个输入片断定义单元(未图示)，用来定义每次输入的起始和终止的时间段。在输入片断定义的时间内完成的输入才是一个输入信息，超过该时间的输入则无法记入本次输入，如果没有输完，则需要重新输入。In an embodiment of the present invention, it may further include an input segment definition unit (not shown), which is used to define the start and end time periods of each input. The input completed within the time defined by the input fragment is an input information, and the input beyond this time cannot be recorded in this input, and if the input is not completed, it needs to be re-entered.
上述说明已经充分揭露了本发明的具体实施方式。需要指出的是，熟悉该领域的技术人员对本发明的具体实施方式所做的任何改动均不脱离本发明的权利要求书的范围。相应地，本发明的权利要求的范围也并不仅仅局限于前述具体实施方式。The above description has fully disclosed the specific implementation manners of the present invention. It should be pointed out that any changes made by those skilled in the art to the specific embodiments of the present invention will not depart from the scope of the claims of the present invention. Accordingly, the scope of the claims of the present invention is not limited only to the foregoing specific embodiments.
Claims (8)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010550092CN102004548B (en) | 2010-11-18 | 2010-11-18 | System and method of inputting information by using image collecting equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010550092CN102004548B (en) | 2010-11-18 | 2010-11-18 | System and method of inputting information by using image collecting equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102004548A CN102004548A (en) | 2011-04-06 |
| CN102004548Btrue CN102004548B (en) | 2013-02-13 |
Family
ID=43811952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010550092Expired - Fee RelatedCN102004548B (en) | 2010-11-18 | 2010-11-18 | System and method of inputting information by using image collecting equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102004548B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5113452A (en)* | 1988-08-23 | 1992-05-12 | Sony Corporation | Hand-written character recognition apparatus and method |
| JPH09102013A (en) | 1995-10-04 | 1997-04-15 | Nec Corp | Handwriting character/graphic reader |
| CN1881994A (en)* | 2006-05-18 | 2006-12-20 | 北京中星微电子有限公司 | Method and apparatus for hand-written input and gesture recognition of mobile apparatus |
| CN101539994A (en)* | 2009-04-16 | 2009-09-23 | 西安交通大学 | Mutually translating system and method of sign language and speech |
- 2010
- 2010-11-18CNCN 201010550092patent/CN102004548B/ennot_activeExpired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5113452A (en)* | 1988-08-23 | 1992-05-12 | Sony Corporation | Hand-written character recognition apparatus and method |
| JPH09102013A (en) | 1995-10-04 | 1997-04-15 | Nec Corp | Handwriting character/graphic reader |
| CN1881994A (en)* | 2006-05-18 | 2006-12-20 | 北京中星微电子有限公司 | Method and apparatus for hand-written input and gesture recognition of mobile apparatus |
| CN101539994A (en)* | 2009-04-16 | 2009-09-23 | 西安交通大学 | Mutually translating system and method of sign language and speech |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102004548A (en) | 2011-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107172296A (en) | A kind of image capturing method and mobile terminal | |
| US20170032219A1 (en) | Methods and devices for picture processing | |
| EP2998960B1 (en) | Method and device for video browsing | |
| CN106537413B (en) | System and method for automatically generating photo summary | |
| CN107395997A (en) | A kind of image pickup method and mobile terminal | |
| EP2079009A1 (en) | Apparatus and methods for a touch user interface using an image sensor | |
| CN106651955A (en) | Method and device for positioning object in picture | |
| CN106650575A (en) | Face detection method and device | |
| CN106372204A (en) | Push message processing method and device | |
| CN105631803B (en) | The method and apparatus of filter processing | |
| CN110266914A (en) | Image capturing method, device, and computer-readable storage medium | |
| WO2012088702A1 (en) | Method and apparatus for providing a mechanism for gesture recognition | |
| CN108416337A (en) | User is reminded to clean the method and device of camera lens | |
| CN107509040A (en) | A kind of photographic method and mobile terminal | |
| CN105763813A (en) | A photographing method, device and intelligent terminal | |
| CN105511777A (en) | Session display method and device of touch display screen | |
| CN106097398A (en) | The detection method of a kind of Moving Objects and mobile terminal | |
| CN107092852A (en) | Pressure detection method and device | |
| KR20110053396A (en) | Terminal and method for providing a user interface using a gesture | |
| CN106990893B (en) | Touch screen operation processing method and device | |
| CN112954212A (en) | Video generation method, device and equipment | |
| EP3293605A1 (en) | Widget displaying method and apparatus for use in flexible display device, computer program and recording medium | |
| WO2020078102A1 (en) | Image enhancement method and apparatus, and computer-readable storage medium | |
| CN104125487A (en) | Method and device for uploading image data | |
| CN105468237A (en) | Screen-shot method in video call and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | Address after:214028 10-storey Building 530 Qingjia Road, Taihu International Science Park, Wuxi New District, Jiangsu Province Patentee after:Zgmicro Corporation Address before:214028 10-storey Building 530 Qingjia Road, Taihu International Science Park, Wuxi New District, Jiangsu Province Patentee before:WUXI VIMICRO Corp. | |
| CP01 | Change in the name or title of a patent holder | ||
| TR01 | Transfer of patent right | Effective date of registration:20240806 Address after:Room 606, Building C, Entrepreneurship Building, No.1 Zhizhi Island Road, High tech Zone, Qingdao City, Shandong Province, China 266112 Patentee after:Vimicro Qingdao Corp. Country or region after:China Address before:214028 10-storey Building 530 Qingjia Road, Taihu International Science Park, Wuxi New District, Jiangsu Province Patentee before:Zgmicro Corporation Country or region before:China | |
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20130213 | |
| CF01 | Termination of patent right due to non-payment of annual fee |