专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2007080133A2 METHOD FOR COMPUTING A FINGERPRINT OF A VIDEO SEQUENCE 审中-公开
标题翻译：计算视频序列指纹的方法
公开(公告)号：WO2007080133A2
公开(公告)日：2007-07-19
申请号：PCT/EP2007/000334
申请日：2007-01-16
申请人： THOMSON LICENSING , LEFEBVRE, Frédéric , DEMARTY, Claire-Hélène , OISEL, Lionel , MASSOUDI, Ayoub
发明人： LEFEBVRE, Frédéric , DEMARTY, Claire-Hélène , OISEL, Lionel , MASSOUDI, Ayoub
IPC分类号： G06F17/30
CPC分类号： G06F17/30799 , G06F2221/0737 , G06K9/00711 , G06K9/4619 , G06K9/4671 , G06K9/50
摘要： The invention concerns a method for computing a fingerprint of a video sequence. The method comprises the steps of - Computation of a visual digest for each frame of the video, - Computation of the distance between the visual digest of each frame of the video in order to detect shots, - Detection, for each detected shot of the video, of a frame, called stable frame, having the smallest content variation of the shot, - Calculation of a local fingerprint for said stable frame.
摘要翻译：本发明涉及一种用于计算视频序列的指纹的方法。该方法包括以下步骤：计算视频的每个帧的视觉摘要， - 计算视频的每个帧的视觉摘要之间的距离以便检测镜头， - 针对每个检测到的视频镜头的检测，具有拍摄的最小内容变化的称为稳定帧的帧， - 计算所述稳定帧的局部指纹。

2. 发明申请

WO2008049851A2 METHOD FOR COMPARING GROUPS OF IMAGES 审中-公开
标题翻译：比较图像组的方法
公开(公告)号：WO2008049851A2
公开(公告)日：2008-05-02
申请号：PCT/EP2007/061385
申请日：2007-10-24
申请人： THOMSON LICENSING , LEFEBVRE, Frédéric , MASSOUDI, Ayoub
发明人： LEFEBVRE, Frédéric , MASSOUDI, Ayoub
CPC分类号： G06K9/00751 , G06F17/30799 , G06K9/6857
摘要： The invention relates to a method for comparing a group of images, called candidate group, with reference groups of images, said reference groups being stored in a database with their representing key frames to which are associated local features and global features. The method comprises the following steps: - detecting an image within said candidate group, called key frame; - computing a global feature of said key frame; - comparing said computed global feature with the global feature of each key frame of the reference group; - if the differences between said computed global feature and each stored global feature are above a predefined threshold then: computing a local feature of said key frame; comparing said computed local feature with the local feature of each key frame of the reference group.
摘要翻译：本发明涉及一种用于将称为候选组的图像组与参考图像组进行比较的方法，所述参考组被存储在数据库中，并且它们表示与关联局部特征的关键帧和全球特征。该方法包括以下步骤： - 检测所述候选组内的图像，称为关键帧; - 计算所述关键帧的全局特征; - 将所述计算的全局特征与参考组的每个关键帧的全局特征进行比较; - 如果所述计算的全局特征与每个存储的全局特征之间的差异高于预定阈值，则：计算所述关键帧的局部特征; 比较所述计算出的局部特征与参考组的每个关键帧的局部特征。

3. 发明申请

WO2010000727A1 METHODS AND APPARATUSES FOR SELECTIVE DATA ENCRYPTION 审中-公开
标题翻译：选择性数据加密的方法和设备
公开(公告)号：WO2010000727A1
公开(公告)日：2010-01-07
申请号：PCT/EP2009/058161
申请日：2009-06-30
申请人： THOMSON LICENSING , MASSOUDI, Ayoub , LEFEBVRE, Frederic
发明人： MASSOUDI, Ayoub , LEFEBVRE, Frederic
IPC分类号： H04N7/16 , H04L29/06 , H04L9/06
CPC分类号： H04N7/1675 , H04L9/065 , H04L63/0428 , H04L2209/12 , H04L2209/34 , H04N21/23476 , H04N21/44055
摘要： A method of encryption, using an encryption key K with key length k, of at least one message M comprising uniformly distributed symbols, k bits are encrypted (830) of messages at least k bits long, while shorter messages are lengthened (840), e.g. by padding or concatenation, to obtain a lengthened message at least k bits long before encryption. The encryption efficiency is thus optimised while the encryption security is retained. The encryption method is particularly suitable for JPEG2000 encoded packets comprising a message M. Also provided are an encryption apparatus (710), a decryption method and a decryption apparatus (910).
摘要翻译：使用包括均匀分布符号的至少一个消息M的具有密钥长度k的加密密钥K的加密方法，至少k位长度加密（830）消息，同时较短消息被延长（840），例如通过填充或级联，在加密之前至少k位获得延长的消息。因此，在保护加密安全性的同时优化加密效率。加密方法特别适用于包含消息M的JPEG2000编码分组。还提供了加密装置（710），解密方法和解密装置（910）。

4. 发明申请

WO2010007021A1 METHOD AND DEVICE FOR KEY GENERATION 审中-公开
标题翻译：用于关键生成的方法和装置
公开(公告)号：WO2010007021A1
公开(公告)日：2010-01-21
申请号：PCT/EP2009/058916
申请日：2009-07-13
申请人： THOMSON LICENSING , KARROUMI, Mohamed , MASSOUDI, Ayoub
发明人： KARROUMI, Mohamed , MASSOUDI, Ayoub
IPC分类号： H04N7/16
CPC分类号： H04N7/165 , H04N21/2347 , H04N21/23473 , H04N21/26613 , H04N21/631
摘要： A method of generating a segment key KSmt from a given basic key K MT and a given modification key K' MT in a key space with M*T keys. The basic key KMT is split into two parts L MT , R MT onto which a one-way function is applied M-m and T-t times, respectively, and the results are combined again to form a target basic key. A one-way function is applied to the modification key K'MT a number of times that corresponds to a distance value z between the given basic key and the segment key; in one preferred embodiment z=(M-m)+(T-t). This result is XOR-ed with the target basic key to obtain the segment key KS mt. Also provided is a device.
摘要翻译：从具有M * T键的密钥空间中的给定基本密钥KMT和给定修改密钥K'MT生成段密钥KSmt的方法。 KMT的基本键分为LMT，RMT两个部分，分别应用M-m和T-t次的单向功能，结果再次组合形成目标基本密钥。向修改密钥K'MT应用与给定基本密钥和段密钥之间的距离值z相对应的次数的单向功能; 在一个优选实施方案中，z =（M-m）+（T-t）。此结果与目标基本密钥XOR-ed，以获得段密钥KSmt。还提供了一种设备。

5. 发明申请

WO2009090258A1 METHOD AND APPARATUS FOR SELECTIVE DATA ENCRYPTION 审中-公开
标题翻译：选择性数据加密的方法和装置
公开(公告)号：WO2009090258A1
公开(公告)日：2009-07-23
申请号：PCT/EP2009/050521
申请日：2009-01-16
申请人： THOMSON LICENSING , MASSOUDI, Ayoub , LEFEBVRE, Frederic , DURAND, Alain
发明人： MASSOUDI, Ayoub , LEFEBVRE, Frederic , DURAND, Alain
IPC分类号： H04N7/16
CPC分类号： H04N7/1675 , H04N19/13 , H04N19/147 , H04N19/154 , H04N19/467 , H04N19/63 , H04N19/70 , H04N21/23476
摘要： A layered audiovisual packet data stream (CNT'), such as one obtained by a JPEG2000 encoder (810), is received together with information (metadata) about the contribution of each packet to the reduction of image distortion. The distortion-to-rate ratio for each packet is calculated (710) and the packets are ordered (720) is descending ratio. The non-encrypted packet having the highest ratio is encrypted (730) until the target distortion is obtained. Also provided is an apparatus (800). In a variant, the data in the packets are substituted by dummy data instead of encrypted.
摘要翻译：诸如由JPEG2000编码器（810）获得的分层视听分组数据流（CNT'）与关于每个分组对于减少图像失真的贡献的信息（元数据）一起被接收。计算每个分组的失真率比率（710），并且分组被排序（720）是下降比率。具有最高比率的非加密分组被加密（730），直到获得目标失真。还提供了一种装置（800）。在一个变体中，分组中的数据被虚拟数据替代而不是加密。

6. 发明申请

WO2012156774A1 METHOD AND APPARATUS FOR DETECTING VISUAL WORDS WHICH ARE REPRESENTATIVE OF A SPECIFIC IMAGE CATEGORY 审中-公开
标题翻译：检测特定图像类别视觉语言的方法和装置
公开(公告)号：WO2012156774A1
公开(公告)日：2012-11-22
申请号：PCT/IB2011/001459
申请日：2011-05-18
申请人： LTU TECHNOLOGIES , DOLLE, Simon , MASSOUDI, Ayoub , ALLUSSE, Yannick , JAHARD, Frédéric , WINTER, Alexandre
发明人： DOLLE, Simon , MASSOUDI, Ayoub , ALLUSSE, Yannick , JAHARD, Frédéric , WINTER, Alexandre
IPC分类号： G06K9/46 , G06K9/62
CPC分类号： G06K9/623 , G06K9/4676
摘要： The present invention concerns a method for detecting visual words which are representative of a specifier image category from a reference codebook obtained from visual local descriptors extracted from training images, said method comprising the folio wing steps: - forming (1) a general training set (S) which gathers images belonging to multiple image categories, - forming (2) a specific category training set (D) which gathers images belonging to the specifier image category to detect, - obtaining (3) a reference codebook from visual local descriptors extracted from images of said general training sets (S), - Computing (4) a distribution of visual words of the reference codebook over the specifier category training set and a distribution of visual words of the reference codebook over the general training set (S), and - determining (5) which visual words of the reference codebook are representative of the specific image category by comparing the two distributions of visual words. The present invention concerns also an apparatus, a computer program and an information storage means.
摘要翻译：本发明涉及一种用于检测视觉词的方法，该视觉词表示从从训练图像中提取的视觉局部描述符获得的参考码本中的说明符图像类别，所述方法包括对开翼形步骤： - 形成（1）一般训练集（ S），其收集属于多个图像类别的图像， - 形成（2）特征类别训练集合（D），其收集属于所述指定者图像类别的图像，以检测， - 从可视局部描述符获取（3）参考码本所述一般训练集（S）的图像， - 计算（4）参考码本的视觉词在指定者类别训练集上的分布以及参考码本在一般训练集（S）上的视觉词的分布，以及 - 通过比较视觉词的两个分布，确定（5）参考码本的哪个视觉词代表特定图像类别。本发明还涉及一种装置，计算机程序和信息存储装置。

7. 发明申请

WO2012004626A1 METHOD AND APPARATUS FOR OBTAINING A SYMMETRY INVARIANT DESCRIPTOR FROM A VISUAL PATCH OF AN IMAGE 审中-公开
标题翻译：从图像的视觉匹配中获取对称性的描述符的方法和装置
公开(公告)号：WO2012004626A1
公开(公告)日：2012-01-12
申请号：PCT/IB2010/002139
申请日：2010-07-06
申请人： LTU TECHNOLOGIES , MASSOUDI, Ayoub , DOLLE, Simon , WINTER, Alexandre , JAHARD, Frédéric , MOULON, Pierre , WENGERT, Christian
发明人： MASSOUDI, Ayoub , DOLLE, Simon , WINTER, Alexandre , JAHARD, Frédéric , MOULON, Pierre , WENGERT, Christian
IPC分类号： G06K9/64 , G06K9/46
CPC分类号： G06K9/4671 , G06K9/6211
摘要： The present invention concerns a method for deriving from an arbitrary local image descriptor a descriptor that is invariant under arbitrary mirror symmetries. For a point of interest, pi, for which the descriptor is to be determined a direction, ODi is determined. The local patch from which the descriptor is to be extracted is mirrored along ODi if a "smaller than" relation does not hold a feature extracted from the left half of the local image patch, in regard of ODi, compared to the right half of the local image patch. Thereby, the local patch is brought into a normalized intrinsic orientation. Thereafter, the descriptor is extracted. Examples include a mirror symmetry invariant version of Lowe's SIFT.
摘要翻译：本发明涉及从任意的本地图像描述符导出在任意镜像对称下不变的描述符的方法。对于需要确定描述符方向的p i，确定OD i。与ODi相比，如果“小于”关系不存在从本地图像补丁的左半部分提取的特征，则与ODi相比，将要提取描述符的本地补丁与ODi相反。本地图片补丁。由此，使局部贴片进入归一化的固有取向。此后，提取描述符。示例包括Lowe's SIFT的镜像对称不变版本。

8. 发明公开

EP1974300A2 METHOD FOR DETERMINING AND FINGERPRINTING A KEY FRAME OF A VIDEO SEQUENCE 审中-公开
标题翻译：程序的视频序列的主要框架确定及指纹图谱
公开(公告)号：EP1974300A2
公开(公告)日：2008-10-01
申请号：EP07717849.9
申请日：2007-01-16
申请人： Thomson Licensing
发明人： LEFEBVRE, Frédéric , DEMARTY, Claire-Hélène , OISEL, Lionel , MASSOUDI, Ayoub
IPC分类号： G06F17/30
CPC分类号： G06F17/30799 , G06F2221/0737 , G06K9/00711 , G06K9/4619 , G06K9/4671 , G06K9/50
摘要： The invention concerns a method for computing a fingerprint of a video sequence. The method comprises the steps of - Computation of a visual digest for each frame of the video, - Computation of the distance between the visual digest of each frame of the video in order to detect shots, - Detection, for each detected shot of the video, of a frame, called stable frame, having the smallest content variation of the shot, - Calculation of a local fingerprint for said stable frame.

9. 发明授权

EP2351368B1 METHOD AND DEVICE FOR KEY GENERATION 有权
公开(公告)号：EP2351368B1
公开(公告)日：2018-08-29
申请号：EP09797484.4
申请日：2009-07-13
申请人： Thomson Licensing
发明人： KARROUMI, Mohamed , MASSOUDI, Ayoub
IPC分类号： H04N21/2347 , H04N21/266 , H04N21/63 , H04N7/16
CPC分类号： H04N7/165 , H04N21/2347 , H04N21/23473 , H04N21/26613 , H04N21/631
摘要： A method of generating a segment key KS mt from a given basic key K MT and a given modification key K' MT in a key space with M*T keys. The basic key K MT is split into two parts L MT , R MT onto which a one-way function is applied M-m and T-t times, respectively, and the results are combined again to form a target basic key. A one-way function is applied to the modification key K' MT a number of times that corresponds to a distance value z between the given basic key and the segment key; in one preferred embodiment z=(M-m)+(T-t). This result is XOR-ed with the target basic key to obtain the segment key KS mt . Also provided is a device.

10. 发明公开

EP2255532A1 METHOD AND APPARATUS FOR SELECTIVE DATA ENCRYPTION 失效
标题翻译： VEFAHREN和设备的选择性数据加密
公开(公告)号：EP2255532A1
公开(公告)日：2010-12-01
申请号：EP09702439.2
申请日：2009-01-16
申请人： Thomson Licensing
发明人： MASSOUDI, Ayoub , LEFEBVRE, Frederic , DURAND, Alain
IPC分类号： H04N7/16
CPC分类号： H04N7/1675 , H04N19/13 , H04N19/147 , H04N19/154 , H04N19/467 , H04N19/63 , H04N19/70 , H04N21/23476
摘要： A layered audiovisual packet data stream (CNT'), such as one obtained by a JPEG2000 encoder (810), is received together with information (metadata) about the contribution of each packet to the reduction of image distortion. The distortion-to-rate ratio for each packet is calculated (710) and the packets are ordered (720) is descending ratio. The non-encrypted packet having the highest ratio is encrypted (730) until the target distortion is obtained. Also provided is an apparatus (800). In a variant, the data in the packets are substituted by dummy data instead of encrypted.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式