公开(公告)号：US20110122137A1

公开(公告)日：2011-05-26

申请号：US12623466

申请日：2009-11-23

Applicant: Jhing-Fa WANG ,  Bo-Wei CHEN ,  Jia-Ching WANG ,  Chia-Hung CHANG

Inventor： Jhing-Fa WANG ,  Bo-Wei CHEN ,  Jia-Ching WANG ,  Chia-Hung CHANG

IPC: G06T11/20 ,  G06F17/21

CPC classification number: G06T11/206 ,  G06F17/30843 ,  G11B27/034 ,  G11B27/28 ,  G11B27/322

Abstract: A video summarized method based on mining the story structure and semantic relations among concept entities has steps of processing a video to generate multiple important shots that are annotated with respective keywords: Performing a concept expansion process by using the keywords to create expansion trees for the annotated shots; rearranging the keywords of the expansion trees and classifying to calculate relations thereof; applying a graph entropy algorithm to determine significant shots and edges interconnected with the shots. Based on the determined result of the graph entropy algorithm, a structured relational graph is built to display the significant shots and edges thereof. Consequently, users can more rapidly browse the content of a video and comprehend if different shots are related.

Abstract translation: 基于挖掘概念实体之间的故事结构和语义关系的视频汇总方法具有处理视频以生成多个重要照片的步骤，这些重要照片用相应的关键字注释：通过使用关键字创建扩展树来创建注释的概念扩展过程 射击 重新布置扩展树的关键字并进行分类以计算其关系; 应用图熵算法来确定与镜头相互连接的重要镜头和边缘。 基于图熵算法的确定结果，建立了结构化关系图，以显示其重要的镜头和边缘。 因此，用户可以更快速地浏览视频的内容，并理解如果不同的镜头相关。

公开(公告)号：US07305337B2

公开(公告)日：2007-12-04

申请号：US10328486

申请日：2002-12-24

Applicant: Jhing-Fa Wang ,  Jia-Ching Wang ,  Yun-Fei Chao ,  Han-Chiang Chen ,  Ming-Chi Shih

Inventor： Jhing-Fa Wang ,  Jia-Ching Wang ,  Yun-Fei Chao ,  Han-Chiang Chen ,  Ming-Chi Shih

IPC: G10L11/04

CPC classification number: G10L19/012 ,  G10L19/08 ,  G10L19/18

Abstract: The present invention includes a method for speech encoding and decoding and a design of speech coder and decoder. The characteristic of speech encoding method relies on the type of data with high compression rate after the whole speech data is compressed. The present invention is able to lower the bit rate of the original speech from 64 Kbps to 1.6 Kbps and provide a bit rate lower than the traditional compression method. It can provide good speech quality, and attain the function of storing the maximum speech data with minimum memory. As to the speech decoding method, some random noises are appropriated added into the exciting source, so that more speech characteristics can be simulated to produce various speech sounds. In addition, the present invention also discloses a coder and a decoder designed by application specific integrated circuit, and the structural design is optimized according to the software. Its operating speed is much faster than the digital signal processor, and suits the system requiring fast computation speed such as multiple line encoding; its cost is also lower than the digital signal processor.

Abstract translation: 本发明包括语音编码和解码的方法以及语音编码器和解码器的设计。 语音编码方法的特点是在整个语音数据压缩之后依赖于具有高压缩率的数据类型。 本发明能够将原始语音的比特率从64Kbps降低到1.6Kbps，并提供比传统压缩方法低的比特率。 它可以提供良好的语音质量，并且具有以最小记忆存储最大语音数据的功能。 对于语音解码方法，将一些随机噪声加入到激励源中，从而可以模拟更多的语音特征以产生各种语音。 此外，本发明还公开了一种由专用集成电路设计的编码器和解码器，并且根据该软件优化结构设计。 其运行速度比数字信号处理器快得多，适合需要快速计算速度的系统，如多行编码; 其成本也低于数字信号处理器。

公开(公告)号：US20070214418A1

公开(公告)日：2007-09-13

申请号：US11486122

申请日：2006-07-14

Applicant: Jhing-Fa Wang ,  Jia-Ching Wang ,  Chen-Yu Chen

Inventor： Jhing-Fa Wang ,  Jia-Ching Wang ,  Chen-Yu Chen

IPC: G06F3/00

CPC classification number: G06F17/30796 ,  G06F17/30802 ,  G06F17/30843 ,  G06K9/00751 ,  Y10S345/951

Abstract: The present invention discloses a video summarization system and the method thereof. A similarity computing apparatus computes the similarity between each frame to obtain multiple similarity values. A key frame extracting apparatus chooses the key frames from the frames wherein the sum of the similarity values between the key frames is a minimum. A feature space mapping apparatus converts the sentences into multiple corresponding sentence vectors and computes the distance between each sentence vector to obtain multiple distance values. A clustering apparatus divides the sentences into multiple clusters according to the distance values and the importance of the sentences, and also applies a splitting step to split the cluster with the highest importance into multiple new clusters. A key sentence extracting apparatus chooses multiple key sentence from the clusters, wherein the sum of the importance of the key sentences is the maximum.

Abstract translation: 本发明公开了一种视频摘要系统及其方法。 相似度计算装置计算每个帧之间的相似度以获得多个相似度值。 关键帧提取装置从帧中选择关键帧，其中关键帧之间的相似度之和为最小。 特征空间映射设备将句子转换为多个对应的句子向量，并计算每个句子向量之间的距离以获得多个距离值。 聚类设备根据距离值和句子的重要性将句子分成多个簇，并且还应用分割步骤将具有最高重要性的群集分割成多个新群集。 关键句提取装置从群集中选择多个关键句，其中关键句子的重要性之和为最大。

公开(公告)号：US08451292B2

公开(公告)日：2013-05-28

申请号：US12623466

申请日：2009-11-23

Applicant: Jhing-Fa Wang ,  Bo-Wei Chen ,  Jia-Ching Wang ,  Chia-Hung Chang

Inventor： Jhing-Fa Wang ,  Bo-Wei Chen ,  Jia-Ching Wang ,  Chia-Hung Chang

IPC: G09G5/00 ,  G06T11/20

CPC classification number: G06T11/206 ,  G06F17/30843 ,  G11B27/034 ,  G11B27/28 ,  G11B27/322

Abstract: A video summarized method based on mining the story structure and semantic relations among concept entities has steps of processing a video to generate multiple important shots that are annotated with respective keywords: Performing a concept expansion process by using the keywords to create expansion trees for the annotated shots; rearranging the keywords of the expansion trees and classifying to calculate relations thereof; applying a graph entropy algorithm to determine significant shots and edges interconnected with the shots. Based on the determined result of the graph entropy algorithm, a structured relational graph is built to display the significant shots and edges thereof. Consequently, users can more rapidly browse the content of a video and comprehend if different shots are related.

Abstract translation: 基于挖掘概念实体之间的故事结构和语义关系的视频汇总方法具有处理视频以生成多个重要照片的步骤，这些重要照片用相应的关键字注释：通过使用关键字创建扩展树来创建注释的概念扩展过程 射击 重新布置扩展树的关键字并进行分类以计算其关系; 应用图熵算法来确定与镜头相互连接的重要镜头和边缘。 基于图熵算法的确定结果，建立了结构化关系图，以显示其重要的镜头和边缘。 因此，用户可以更快速地浏览视频的内容，并理解如果不同的镜头相关。

公开(公告)号：US20070094020A1

公开(公告)日：2007-04-26

申请号：US11253636

申请日：2005-10-20

Applicant: Jhing-Fa Wang ,  Po-Chuan Lin ,  Li-Chang Wen

Inventor： Jhing-Fa Wang ,  Po-Chuan Lin ,  Li-Chang Wen

IPC: G10L15/00

CPC classification number: G10L15/08

Abstract: A method and system used to determine the similarity between an input speech data and a sample speech data is provided. First, the input speech data is segmented into a plurality of input speech frames and the sample speech data is segmented into a plurality of sample speech frames. Then, the input speech frames and the sample speech frames are used to build a matching matrix, wherein the matching matrix comprises the distance values between each of the input speech frames and each of the sample speech frames. Next, the distance values are used to calculate a matching score. Finally, the similarity between the input speech data and the sample speech data is determined according to this matching score.

Abstract translation: 提供了用于确定输入语音数据和样本语音数据之间的相似性的方法和系统。 首先，将输入语音数据分割为多个输入语音帧，并将样本语音数据分割为多个采样语音帧。 然后，使用输入语音帧和采样语音帧构建匹配矩阵，其中匹配矩阵包括每个输入语音帧与每个采样语音帧之间的距离值。 接下来，使用距离值来计算匹配分数。 最后，根据该匹配分数来确定输入语音数据和样本语音数据之间的相似度。

公开(公告)号：US08204114B2

公开(公告)日：2012-06-19

申请号：US12167653

申请日：2008-07-03

Applicant: Jhing-Fa Wang ,  Wei-Guang Lin ,  An-Chao Tsai

Inventor： Jhing-Fa Wang ,  Wei-Guang Lin ,  An-Chao Tsai

IPC: H04B1/66

CPC classification number: H04N19/11 ,  H04N19/14 ,  H04N19/176 ,  H04N19/19 ,  H04N19/593 ,  H04N19/61

Abstract: A block intra prediction direction detection algorithm comprises acts of dividing a block, finding directions from edge assent rules, determining a main edge of the block, selecting prediction modes from the main edge, choosing base prediction modes and using all unique selected and base prediction modes in intra prediction. The algorithms comprise a 4×4 block intra prediction direction detection algorithm, a 16×16 luminance block intra prediction direction detection algorithm and an 8×8 chrominance block intra prediction direction detection algorithm.

Abstract translation: 块内预测方向检测算法包括划分块的动作，从边缘同意规则查找方向，确定块的主边缘，从主边缘选择预测模式，选择基本预测模式并使用所有唯一的选择和基本预测模式 在帧内预测。 算法包括4×4块帧内预测方向检测算法，16×16亮度块帧内预测方向检测算法和8×8色度块帧内预测方向检测算法。

公开(公告)号：US07613365B2

公开(公告)日：2009-11-03

申请号：US11486122

申请日：2006-07-14

Applicant: Jhing-Fa Wang ,  Jia-Ching Wang ,  Chen-Yu Chen

Inventor： Jhing-Fa Wang ,  Jia-Ching Wang ,  Chen-Yu Chen

IPC: G06K9/54

CPC classification number: G06F17/30796 ,  G06F17/30802 ,  G06F17/30843 ,  G06K9/00751 ,  Y10S345/951

Abstract: The present invention discloses a video summarization system and the method thereof. A similarity computing apparatus computes the similarity between each frame to obtain multiple similarity values. A key frame extracting apparatus chooses the key frames from the frames wherein the sum of the similarity values between the key frames is a minimum. A feature space mapping apparatus converts the sentences into multiple corresponding sentence vectors and computes the distance between each sentence vector to obtain multiple distance values. A clustering apparatus divides the sentences into multiple clusters according to the distance values and the importance of the sentences, and also applies a splitting step to split the cluster with the highest importance into multiple new clusters. A key sentence extracting apparatus chooses multiple key sentence from the clusters, wherein the sum of the importance of the key sentences is the maximum.

Abstract translation: 本发明公开了一种视频摘要系统及其方法。 相似度计算装置计算每个帧之间的相似度以获得多个相似度值。 关键帧提取装置从帧中选择关键帧，其中关键帧之间的相似度之和为最小。 特征空间映射设备将句子转换为多个对应的句子向量，并计算每个句子向量之间的距离以获得多个距离值。 聚类设备根据距离值和句子的重要性将句子分成多个簇，并且还应用分割步骤将具有最高重要性的群集分割成多个新群集。 关键句提取装置从群集中选择多个关键句，其中关键句子的重要性之和为最大。

公开(公告)号：US07418131B2

公开(公告)日：2008-08-26

申请号：US11174671

申请日：2005-07-06

Applicant: Jhing-Fa Wang ,  Han-Jen Hsu ,  Shang-Chia Liao

Inventor： Jhing-Fa Wang ,  Han-Jen Hsu ,  Shang-Chia Liao

IPC: G06K9/00

CPC classification number: G06T11/001 ,  G06T5/005 ,  G06T7/90

Abstract: An image-capturing device and method for removing strangers from an image are described. First, a first image is input. Then, a control module determines if an unwanted object processing step is needed, and obtains a result. If the result is no, the first image is directly sent to an output module. If the result is yes, an image-identifying module begins to identify the target-image and the unwanted object in the first image, and then, an unwanted object processing module starts the step to process unwanted images. The unwanted object processing step can remove the unwanted object from an image and fill the left lacuna region. Afterwards, a second image is produced and sent to the output module.

Abstract translation: 描述了一种用于从图像中去除陌生人的图像捕获装置和方法。 首先，输入第一个图像。 然后，控制模块确定是否需要不需要的对象处理步骤，并获得结果。 如果结果为否，则将第一个图像直接发送到输出模块。 如果结果为是，则图像识别模块开始识别第一图像中的目标图像和不需要的对象，然后，不需要的对象处理模块开始处理不想要的图像的步骤。 不需要的对象处理步骤可以从图像中去除不需要的对象并填充左侧的空白区域。 之后，产生第二个图像并将其发送到输出模块。

公开(公告)号：US20130261879A1

公开(公告)日：2013-10-03

申请号：US13476518

申请日：2012-05-21

Applicant: Shi-Huang Chen ,  Jhing-Fa Wang ,  Tzyh-Jong Shang

Inventor： Shi-Huang Chen ,  Jhing-Fa Wang ,  Tzyh-Jong Shang

IPC: G06F7/00

CPC classification number: G01M17/025 ,  G01M17/007

Abstract: A method for diagnosing breakdown cause of a vehicle is disclosed. In the method, several sound signals are sensed respectively with several sound sensing devices, which are respectively installed at several zones among the vehicle, from the vehicle. A current driving status of the vehicle is obtained through an electrical control unit (ECU) of the vehicle. Determine a sound source of the vehicle according to the sound signals. A breakdown cause of the vehicle is diagnosed according to the sound signals, the current driving status and the sound source.

Abstract translation: 公开了一种用于诊断车辆故障原因的方法。 在该方法中，分别感测到几个声音传感装置，其分别安装在车辆之间的几个区域。 通过车辆的电气控制单元（ECU）获得车辆的当前驾驶状态。 根据声音信号确定车辆的声源。 车辆故障原因根据声音信号，当前驾驶状况和声源进行诊断。

公开(公告)号：US07774203B2

公开(公告)日：2010-08-10

申请号：US11589772

申请日：2006-10-31

Applicant: Jhing-Fa Wang ,  Chao-Ching Huang ,  Dian-Jia Wu

Inventor： Jhing-Fa Wang ,  Chao-Ching Huang ,  Dian-Jia Wu

IPC: G10L21/00

CPC classification number: G10L25/78

Abstract: The present invention discloses an audio signal segmentation algorithm comprising the following steps. First, an audio signal is provided. Then, an audio activity detection (AAD) step is applied to divide the audio signal into at least one noise segment and at least one noisy audio segment. Then, an audio feature extraction step is used on the noisy audio segment to obtain multiple audio features. Then, a smoothing step is applied. Then, multiple speech frames and multiple music frames are discriminated. The speech frames and the music frames compose at least one speech segment and at least one music segment. Finally, the speech segment and the music segment are segmented from the noisy audio segment.

Abstract translation: 本发明公开了一种包括以下步骤的音频信号分割算法。 首先，提供音频信号。 然后，应用音频活动检测（AAD）步骤将音频信号划分成至少一个噪声段和至少一个噪声音频段。 然后，在噪声音频段上使用音频特征提取步骤以获得多个音频特征。 然后，应用平滑步骤。 然后，区分多个语音帧和多个音乐帧。 语音帧和音乐帧组成至少一个语音段和至少一个音乐段。 最后，语音段和音乐段是从嘈杂的音频段分段的。