公开(公告)号：US08306282B2

公开(公告)日：2012-11-06

申请号：US12350378

申请日：2009-01-08

申请人： Hong-Long Chou ,  Tai-Chang Yang ,  Yin-Pin Chang

发明人： Hong-Long Chou ,  Tai-Chang Yang ,  Yin-Pin Chang

IPC分类号： G06K9/00

CPC分类号： G06K9/6282 ,  G06K9/00221 ,  G06K9/6807

摘要： A hierarchical face recognition training method and a hierarchical face recognition method thereof for performing a face feature recognition on an image under detection. The method includes a training process and a recognition process. The recognition method includes the steps. A plurality of training samples is obtained. The training samples are subdivided into a plurality of sub-image categories according to a plurality of angle intervals, and the training of a plurality of face features performs on a corresponding sub-image detector of each of the sub-image categories. The training measures performed repeatedly to generate sub-image categories at a sub-level of the sub-image categories. The training method includes the steps. An image under detection is loaded. A similarity of each of sub-image detectors compares according to the image under detection, and the sub-image detector having the highest similarity is selected. The face recognition measures performed repeatedly on the selected sub-image detector.

摘要翻译： 一种用于对检测到的图像执行面部特征识别的分层面部识别训练方法和分层面部识别方法。 该方法包括训练过程和识别过程。 识别方法包括步骤。 获得多个训练样本。 训练样本根据多个角度间隔被细分为多个子图像类别，并且多个脸部特征的训练在每个子图像类别的相应子图像检测器上执行。 重复执行的训练措施，以在子图像类别的子级别生成子图像类别。 训练方法包括步骤。 检测到的图像被加载。 每个子图像检测器的相似度根据检测到的图像进行比较，并且选择具有最高相似度的子图像检测器。 在所选择的子图像检测器上重复执行面部识别措施。

公开(公告)号：US08279265B2

公开(公告)日：2012-10-02

申请号：US12472064

申请日：2009-05-26

申请人： Chia-Chun Tseng ,  Hong-Long Chou

发明人： Chia-Chun Tseng ,  Hong-Long Chou

IPC分类号： H04N7/00

CPC分类号： H04N5/232 ,  H04N5/144 ,  H04N5/23238 ,  H04N5/23293

摘要： An automatic capturing method of a panoramic image for a digital camera panoramic image is presented. In the method, a motion vector value of an alignment image selected from a first image captured by the digital camera in a real-time image is continuously tracked, calculated, and accumulated to obtain an accumulated motion vector value. When the accumulated motion vector value reaches a preset threshold value, the digital camera is automatically driven to capture a second image, so as to stitch and blend the first image and the second image into a panoramic image. Through the automatic image capture mode, operations for capturing the panoramic image are simplified.

摘要翻译： 提出了一种用于数码相机全景图像的全景图像的自动捕获方法。 在该方法中，连续跟踪，计算和累加从数字照相机在实时图像中捕获的第一图像中选择的对准图像的运动矢量值，以获得累积运动矢量值。 当累积运动矢量值达到预设阈值时，数字照相机被自动驱动以捕获第二图像，以便将第一图像和第二图像缝合并混合成全景图像。 通过自动图像拍摄模式，简化了拍摄全景图像的操作。

公开(公告)号：US20120170817A1

公开(公告)日：2012-07-05

申请号：US13074557

申请日：2011-03-29

申请人： TAI-CHANG YANG ,  YIN-PIN CHANG ,  WEN-YAN CHANG ,  HONG-LONG CHOU

发明人： TAI-CHANG YANG ,  YIN-PIN CHANG ,  WEN-YAN CHANG ,  HONG-LONG CHOU

IPC分类号： G06K9/00

CPC分类号： G06K9/00832 ,  B60H2001/00992 ,  G06K9/00288

摘要： A vehicle apparatus control system and method thereof are disclosed. The vehicle apparatus control system comprises a data storage module, an image capturing module, a face recognition module and a control module. The data storage module stores multiple registered users' facial feature parameters and vehicle apparatus setting parameters, and integration setting data. The face recognition module detects several facial images contained in the captured image and recognizes the users corresponding to the face images according to the facial feature parameters stored in data storage module. The control module set a vehicle apparatus according to the integration setting data, and the corresponding users' vehicle apparatus setting parameters.

摘要翻译： 公开了一种车辆装置控制系统及其方法。 车辆装置控制系统包括数据存储模块，图像捕获模块，人脸识别模块和控制模块。 数据存储模块存储多个注册用户的面部特征参数和车辆设备设置参数，以及积分设置数据。 面部识别模块根据存储在数据存储模块中的面部特征参数，检测拍摄图像中包含的几张面部图像，并识别对应于面部图像的用户。 控制模块根据积分设定数据和对应的用户的车辆装置设定参数设定车辆装置。

公开(公告)号：US07876364B2

公开(公告)日：2011-01-25

申请号：US12190744

申请日：2008-08-13

申请人： Chung-Ta Wu ,  Hong-Long Chou ,  Yen-Ping Teng

发明人： Chung-Ta Wu ,  Hong-Long Chou ,  Yen-Ping Teng

IPC分类号： H04N9/73 ,  H04N5/228 ,  H04N5/217 ,  H04N9/64

CPC分类号： H04N9/646 ,  G06T5/50 ,  H04N9/045

摘要： A false color suppression method for a digital image is described. The method is performed in a digital camera, for suppressing the false color of the digital image shot by the digital camera. The method includes separating a luminance part and a chrominance part of a digital image; extracting the chrominance part, and calculating a first color gamut component and a second color gamut component in the chrominance part; setting a critical value according to a photosensitivity during shooting by the digital camera; performing a corresponding pixel uniformization action on the pixel according to a relation between a difference between the pixel and adjacent neighboring pixels and the critical value respectively for the first color gamut component and the second color gamut component; and combining the uniformized chrominance part and the luminance part of the digital image to a suppressed image.

摘要翻译： 描述了用于数字图像的假色抑制方法。 该方法在数字照相机中执行，用于抑制数字照相机拍摄的数字图像的假色。 该方法包括分离数字图像的亮度部分和色度部分; 提取色度部分，并计算色度部分中的第一色域分量和第二色域分量; 根据数码相机拍摄期间的光敏度设置临界值; 根据所述像素和相邻相邻像素之间的差异以及所述第一色域分量和所述第二色域分量的临界值之间的关系，对所述像素执行相应的像素均匀化动作; 并将均匀化的色度部分和数字图像的亮度部分组合成抑制图像。

公开(公告)号：US20100194852A1

公开(公告)日：2010-08-05

申请号：US12472064

申请日：2009-05-26

申请人： Chia Chun Tseng ,  Hong Long Chou

发明人： Chia Chun Tseng ,  Hong Long Chou

IPC分类号： H04N7/00

CPC分类号： H04N5/232 ,  H04N5/144 ,  H04N5/23238 ,  H04N5/23293

摘要： An automatic capturing method of a panoramic image for a digital camera panoramic image is presented. In the method, a motion vector value of an alignment image selected from a first image captured by the digital camera in a real-time image is continuously tracked, calculated, and accumulated to obtain an accumulated motion vector value. When the accumulated motion vector value reaches a preset threshold value, the digital camera is automatically driven to capture a second image, so as to stitch and blend the first image and the second image into a panoramic image. Through the automatic image capture mode, operations for capturing the panoramic image are simplified.

摘要翻译： 提出了一种用于数码相机全景图像的全景图像的自动捕获方法。 在该方法中，连续跟踪，计算和累加从数字照相机在实时图像中捕获的第一图像中选择的对准图像的运动矢量值，以获得累积运动矢量值。 当累积运动矢量值达到预设阈值时，数字照相机被自动驱动以捕获第二图像，以便将第一图像和第二图像缝合并混合成全景图像。 通过自动图像拍摄模式，简化了拍摄全景图像的操作。

公开(公告)号：US20100166310A1

公开(公告)日：2010-07-01

申请号：US12424750

申请日：2009-04-16

申请人： CHEN HUNG CHAN ,  HONG LONG CHOU

发明人： CHEN HUNG CHAN ,  HONG LONG CHOU

IPC分类号： G06K9/00

CPC分类号： G06K9/00234

摘要： A method of establishing a skin color model includes the following steps. A human face detecting procedure is performed on an input image, and a human face area in the input image is circled through a selecting window. A skin color model is established by using a Gaussian probability distribution function (PDF) according to color information in the selecting window. When the skin color model established in the above step is applied to skin color detection, pixels having the skin color in the input image are detected through the skin color model and a Mahalanobis distance computing procedure.

摘要翻译： 建立皮肤颜色模型的方法包括以下步骤。 对输入图像执行人脸检测过程，并且输入图像中的人脸区域通过选择窗口圈出。 根据选择窗口中的颜色信息，使用高斯概率分布函数（PDF）建立肤色模型。 当将上述步骤中建立的皮肤颜色模型应用于皮肤颜色检测时，通过皮肤颜色模型和马氏距离计算程序检测输入图像中具有皮肤颜色的像素。

公开(公告)号：US07676149B2

公开(公告)日：2010-03-09

申请号：US11732247

申请日：2007-04-03

申请人： Chung-Ta Wu ,  Hong-Long Chou

发明人： Chung-Ta Wu ,  Hong-Long Chou

IPC分类号： G03B7/08

CPC分类号： G03B7/28 ,  G03B7/09979 ,  H04N5/23212

摘要： A system for backlight detection using the brightness values of the subareas in a focus area and method therefor are provided, which are applicable to an image capture device. The focus area is divided into a plurality of subareas and the brightness values of each of the subareas are calculated. Then, the brightness values of each of the subareas are converted into 0 and 1 codes, and then the codes are combined to generate the codes representing the entire focus area. The status values corresponding to each of the codes are determined with reference to a backlight detection table established in advance, so as to determine whether an object to be shot is in a backlight condition.

摘要翻译： 提供一种使用聚焦区域中的子区域的亮度值进行背光检测的系统及其方法，其可应用于图像捕获装置。 聚焦区域被分成多个子区域，并且计算每个子区域的亮度值。 然后，将每个子区域的亮度值转换为0和1个代码，然后将代码组合以生成表示整个焦点区域的代码。 参照预先设定的背光检测表来决定与各代码相对应的状态值，判断被拍摄对象是否处于背光状态。

公开(公告)号：US20090268041A1

公开(公告)日：2009-10-29

申请号：US12425441

申请日：2009-04-17

申请人： Hong-Long Chou ,  Chih-Yuan Yang

发明人： Hong-Long Chou ,  Chih-Yuan Yang

IPC分类号： H04N5/228

CPC分类号： H04N5/23248

摘要： A digital image processing method for correcting a shaking blur corrects a blurred image caused by a shake when a user shoots an image with a digital camera, which includes the following steps obtaining a safe shutter time of the digital camera; performing an exposure adjustment procedure, for adjusting an aperture and a ISO speed of the digital camera respectively, and obtaining a shutter time of the digital camera after being adjusted; performing a shooting procedure; shooting a plurality of digital images, if the shutter time of the digital camera is greater than the safe shutter time; and then performing an image compensation procedure according to the digital images, to align the same image object in the digital images and then to overlay each pixel of the digital images one by one, thereby outputting an output image.

摘要翻译： 当用户使用数码相机拍摄图像时，用于校正抖动模糊的数字图像处理方法校正由抖动引起的模糊图像，其包括获得数字照相机的安全快门时间的以下步骤; 执行曝光调整程序，用于分别调节数字照相机的光圈和ISO感光度，并在调整数字相机之后获得快门时间; 执行射击程序; 如果数码相机的快门时间大于安全快门时间，则拍摄多个数字图像; 然后根据数字图像执行图像补偿过程，以对齐数字图像中的相同图像对象，然后逐个覆盖数字图像的每个像素，从而输出输出图像。

公开(公告)号：US20090169067A1

公开(公告)日：2009-07-02

申请号：US12344813

申请日：2008-12-29

申请人： Yin-Pin CHANG ,  Tai-Chang YANG ,  Hong-Long CHOU

发明人： Yin-Pin CHANG ,  Tai-Chang YANG ,  Hong-Long CHOU

IPC分类号： G06K9/00

CPC分类号： G06K9/00295

摘要： Face detection and tracking method is executed by a computer or a microprocessor with computing capability for identifying human faces and positions thereof in image frames. First, face detection is performed to detect human faces in a plurality of frames. Then, face tracking is performed on each of the frames to track the detected human faces and record positions of these human faces. Afterward, face detection on the image frames is again performed every few frames, skipping the positions of the human faces that have been recorded, so as to quickly search for other human faces that might be newly added.

摘要翻译： 面部检测和跟踪方法由具有计算能力的计算机或微处理器执行，用于在图像帧中识别人脸和位置。 首先，进行脸部检测以检测多个帧中的人脸。 然后，对每个帧执行脸部跟踪以跟踪检测到的人脸并记录这些人脸的位置。 之后，每隔几帧再次执行图像帧上的脸部检测，跳过已经记录的人脸的位置，以便快速搜索可能新添加的其他人脸。

公开(公告)号：US20090167906A1

公开(公告)日：2009-07-02

申请号：US12190744

申请日：2008-08-13

申请人： Chung-Ta WU ,  Hong-Long CHOU ,  Yen-Ping TENG

发明人： Chung-Ta WU ,  Hong-Long CHOU ,  Yen-Ping TENG

IPC分类号： H04N9/64

CPC分类号： H04N9/646 ,  G06T5/50 ,  H04N9/045

摘要： A false color suppression method for a digital image is described. The method is performed in a digital camera, for suppressing the false color of the digital image shot by the digital camera. The method includes separating a luminance part and a chrominance part of a digital image; extracting the chrominance part, and calculating a first color gamut component and a second color gamut component in the chrominance part; setting a critical value according to a photosensitivity during shooting by the digital camera; performing a corresponding pixel uniformization action on the pixel according to a relation between a difference between the pixel and adjacent neighboring pixels and the critical value respectively for the first color gamut component and the second color gamut component; and combining the uniformized chrominance part and the luminance part of the digital image to a suppressed image.

摘要翻译： 描述了用于数字图像的假色抑制方法。 该方法在数字照相机中执行，用于抑制数字照相机拍摄的数字图像的假色。 该方法包括：分离数字图像的亮度部分和色度部分; 提取色度部分，并计算色度部分中的第一色域分量和第二色域分量; 根据数码相机拍摄期间的光敏度设置临界值; 根据所述像素和相邻相邻像素之间的差异以及所述第一色域分量和所述第二色域分量的临界值之间的关系，对所述像素执行相应的像素均匀化动作; 并将均匀化的色度部分和数字图像的亮度部分组合成抑制图像。