公开(公告)号：US20100104148A1

公开(公告)日：2010-04-29

申请号：US12433883

申请日：2009-04-30

申请人： Alan C. Bovik ,  Mia K. Markey ,  Mehul Sampat

发明人： Alan C. Bovik ,  Mia K. Markey ,  Mehul Sampat

IPC分类号： G06K9/40

CPC分类号： G06K9/4633 ,  G06K2209/053 ,  G06T5/20 ,  G06T7/0012 ,  G06T7/44 ,  G06T2207/10116 ,  G06T2207/30068

摘要： A method and apparatus detects one or more spiculated masses in an image using a processor. The image is received in the processor. The received image is filtered using one or more Gaussian filters to detect one or more central mass regions. The received image is also filtered using one or more spiculated lesion filters to detect where the one or more spiculated masses converge. In addition, the received image is filtered using one or more Difference-of-Gaussian filters to suppress one or more linear structures. An enhanced image showing the detected spiculated masses is created by combining an output from all of the filtering steps. The enhanced image is then provided to an output of the processor.

摘要翻译： 方法和装置使用处理器来检测图像中的一个或多个打印质量。 图像在处理器中被接收。 使用一个或多个高斯滤波器对接收到的图像进行滤波以检测一个或多个中心质量区域。 接收到的图像也使用一个或多个密封的病变过滤器进行过滤，以检测一个或多个发丝质量会聚的位置。 另外，使用一个或多个高斯差分滤波器对接收到的图像进行滤波以抑制一个或多个线性结构。 通过组合来自所有过滤步骤的输出来创建显示检测到的打印质量的增强图像。 然后将增强的图像提供给处理器的输出。

公开(公告)号：US08164039B2

公开(公告)日：2012-04-24

申请号：US12433883

申请日：2009-04-30

申请人： Alan C. Bovik ,  Mia K. Markey ,  Mehul Sampat

发明人： Alan C. Bovik ,  Mia K. Markey ,  Mehul Sampat

IPC分类号： H01L27/00

CPC分类号： G06K9/4633 ,  G06K2209/053 ,  G06T5/20 ,  G06T7/0012 ,  G06T7/44 ,  G06T2207/10116 ,  G06T2207/30068

摘要： A method and apparatus detects one or more spiculated masses in an image using a processor. The image is received in the processor. The received image is filtered using one or more Gaussian filters to detect one or more central mass regions. The received image is also filtered using one or more spiculated lesion filters to detect where the one or more spiculated masses converge. In addition, the received image is filtered using one or more Difference-of-Gaussian filters to suppress one or more linear structures. An enhanced image showing the detected spiculated masses is created by combining an output from all of the filtering steps. The enhanced image is then provided to an output of the processor.

摘要翻译： 方法和装置使用处理器来检测图像中的一个或多个打印质量。 图像在处理器中被接收。 使用一个或多个高斯滤波器对接收到的图像进行滤波以检测一个或多个中心质量区域。 接收到的图像也使用一个或多个螺旋状的病变滤器进行过滤，以检测一个或多个刺激的质量在哪里收敛。 另外，使用一个或多个高斯差分滤波器对接收到的图像进行滤波以抑制一个或多个线性结构。 通过组合来自所有过滤步骤的输出来创建显示检测到的打印质量的增强图像。 然后将增强的图像提供给处理器的输出。

公开(公告)号：US08457414B2

公开(公告)日：2013-06-04

申请号：US12632389

申请日：2009-12-07

申请人： Sina Jahanbin ,  Alan C. Bovik ,  Eduardo Perez ,  Dinesh Nair

发明人： Sina Jahanbin ,  Alan C. Bovik ,  Eduardo Perez ,  Dinesh Nair

IPC分类号： G06T9/62

CPC分类号： G06K9/52 ,  G06T7/0004 ,  G06T7/45 ,  G06T2207/20016 ,  G06T2207/20064

摘要： Method for detecting textural defects in an image. The image, which may have an irregular visual texture, may be received. The image may be decomposed into a plurality of subbands. The image may be portioned into a plurality of partitions. A plurality of grey-level co-occurrence matrices (GLCMs) may be determined for each partition. A plurality of second-order statistical attributes may be extracted for each GLCM. A feature vector may be constructed for each partition, where the feature vector includes the second order statistical attributes for each GLCM for the partition. Each partition may be classified based on the feature vector for the respective partition. Classification of the partitions may utilize a one-class support vector machine, and may determine if a defect is present in the image.

摘要翻译： 用于检测图像中的纹理缺陷的方法。 可以接收可能具有不规则视觉纹理的图像。 图像可以被分解成多个子带。 图像可以分成多个分区。 可以为每个分区确定多个灰度共生矩阵（GLCM）。 可以为每个GLCM提取多个二阶统计属性。 可以为每个分区构造特征向量，其中特征向量包括用于分区的每个GLCM的二阶统计属性。 可以基于相应分区的特征向量对每个分区进行分类。 分区的分类可以利用一类支持向量机，并且可以确定图像中是否存在缺陷。

公开(公告)号：US20110026804A1

公开(公告)日：2011-02-03

申请号：US12632389

申请日：2009-12-07

申请人： Sina Jahanbin ,  Alan C. Bovik ,  Eduardo Perez ,  Dinesh Nair

发明人： Sina Jahanbin ,  Alan C. Bovik ,  Eduardo Perez ,  Dinesh Nair

IPC分类号： G06K9/00

CPC分类号： G06K9/52 ,  G06T7/0004 ,  G06T7/45 ,  G06T2207/20016 ,  G06T2207/20064

摘要： Method for detecting textural defects in an image. The image, which may have an irregular visual texture, may be received. The image may be decomposed into a plurality of subbands. The image may be portioned into a plurality of partitions. A plurality of grey-level co-occurrence matrices (GLCMs) may be determined for each partition. A plurality of second-order statistical attributes may be extracted for each GLCM. A feature vector may be constructed for each partition, where the feature vector includes the second order statistical attributes for each GLCM for the partition. Each partition may be classified based on the feature vector for the respective partition. Classification of the partitions may utilize a one-class support vector machine, and may determine if a defect is present in the image.

摘要翻译： 用于检测图像中的纹理缺陷的方法。 可以接收可能具有不规则视觉纹理的图像。 图像可以被分解成多个子带。 图像可以分成多个分区。 可以为每个分区确定多个灰度共生矩阵（GLCM）。 可以为每个GLCM提取多个二阶统计属性。 可以为每个分区构造特征向量，其中特征向量包括用于分区的每个GLCM的二阶统计属性。 可以基于相应分区的特征向量对每个分区进行分类。 分区的分类可以利用一类支持向量机，并且可以确定图像中是否存在缺陷。

公开(公告)号：US5282255A

公开(公告)日：1994-01-25

申请号：US717214

申请日：1991-06-17

申请人： Alan C. Bovik ,  Dapang Chen

发明人： Alan C. Bovik ,  Dapang Chen

IPC分类号： G06T9/00 ,  H04N1/41 ,  H04N7/26 ,  H04N7/28 ,  G06K9/36 ,  G06K9/46 ,  H04N7/12

CPC分类号： H04N19/94 ,  H04N19/98 ,  H04N19/13 ,  H04N19/60 ,  H04N19/91

摘要： An improved method for coding and decoding still or moving visual pattern images by partitioning images into blocks or cubes, respectively, and coding each image separately according to visually significant responses of the human eye. Coding is achieved by calculating and subtracting a mean intensity value from digital numbers within each block or cube and detecting visually perceivable edge locations within the resultant residual sub-image. If a visually perceivable edge is contained within the block or cube, gradient magnitude and orientation at opposing sides of the edge within each edge block or cube are calculated and appropriately coded. If no perceivable edge is contained within the block or cube, the sub-image is coded as a uniform intensity block. Decoding requires receiving coded mean intensity value, gradient magnitude and pattern code, and then decoding a combination of these three indicia to be arranged in an orientation substantially similar to the original digital image or original sequence of digital images. Coding and decoding can be accomplished in a hierarchical pattern. Further, hierarchical processing can be programmably manipulated according to user-defined criteria.

摘要翻译： 一种改进的方法，用于分别将图像分割成块或多维数据块，依次或者移动视觉图形图像进行编码和解码，并根据人眼视觉上的显着响应分别对每个图像进行编码。 通过从每个块或多维数据集中的数字数字计算和减去平均强度值来实现编码，并且在所得残留子图像内检测视觉上可感知的边缘位置。 如果视觉上可感知的边缘包含在块或立方体内，则计算并适当地编码每个边缘块或立方体内的边缘的相对侧处的梯度大小和取向。 如果在块或立方体内没有包含可感知的边缘，则子图像被编码为均匀的强度块。 解码需要接收经编码的平均强度值，梯度幅度和图案码，然后对这三个标记的组合进行解码，以便以与原始数字图像或原始数字图像序列基本相似的方向排列。 编码和解码可以以分层模式完成。 此外，可以根据用户定义的标准可编程地操作分层处理。