-
公开(公告)号:KR101035365B1
公开(公告)日:2011-05-20
申请号:KR1020100010647
申请日:2010-02-04
Applicant: 서강대학교산학협력단
CPC classification number: H04N17/004 , H04N19/132 , H04N19/154 , H04N19/164
Abstract: PURPOSE: An image quality evaluating apparatus which uses CS(Compressive Sensing) is provided to apply CS to a distortion map and to reduce calculation time. CONSTITUTION: A distortion map generator(210) generates a distortion map. An image quality measure generator(220) applies a CS(Compressive Sensing, Compressive Sampling, Compressed Sensing, or Sparse Sampling) measurement matrix to the distortion map. A regression analysis unit(230) scales image quality evaluating degree by using regression analysis. A performance evaluator(240) evaluates similarity between scaled image quality degree and DMOS(Difference of Mean Opinion Score).
Abstract translation: 目的:提供使用CS(压缩感知)的图像质量评估装置,以将CS应用于失真图并减少计算时间。 构成:失真图生成器(210)生成失真图。 图像质量测量发生器(220)将CS(压缩感测,压缩采样,压缩感测或稀疏采样)测量矩阵应用于失真图。 回归分析单元(230)通过使用回归分析来缩放图像质量评估度。 性能评估者(240)评估了缩放图像质量度与DMOS(平均意见得分的差异)之间的相似度。
-
公开(公告)号:KR1020110082942A
公开(公告)日:2011-07-20
申请号:KR1020100002890
申请日:2010-01-12
Applicant: 서강대학교산학협력단
IPC: G06T7/00
CPC classification number: G06T7/0002 , G06T2207/30168
Abstract: PURPOSE: A method and apparatus for evaluating an image are provided to supply excellent quantization code and to facilitate hardware implement for image evaluation. CONSTITUTION: An original image and a deteriorated image are filtered(S520). A phase quantization code is generated from the filtering result(S530). A hamming distance between a phase quantization code and a deterioration code(S540). The image quality is evaluated by using the calculated hamming distance(S550).
Abstract translation: 目的:提供一种用于评估图像的方法和装置,以提供优异的量化代码,并且便于图像评估的硬件实现。 构成:对原始图像和劣化图像进行滤波(S520)。 从滤波结果生成相位量化代码(S530)。 相位量化码与劣化码之间的汉明距离(S540)。 通过使用计算的汉明距离来评估图像质量(S550)。
-
公开(公告)号:KR101092650B1
公开(公告)日:2011-12-13
申请号:KR1020100002890
申请日:2010-01-12
Applicant: 서강대학교산학협력단
IPC: G06T7/00
CPC classification number: G06T7/0002 , G06T2207/30168
Abstract: Provided is a method for assessing image quality using quantization codes, which includes: filtering an original image and a distorted image; generating phase quantization codes from the filtering result; calculating a Hamming difference between the phase quantization code of the original image and the phase quantization code of the distorted image; and assessing image quality of the distorted image by using the calculated Hamming difference. According to the present disclosure, since pixel values of the original image and the distorted image are mapped onto a quantized complex plane and then binary code operation is performed, it is possible to easily implement image quality assessing hardware and also ensure excellent image quality assessing performance.
-
公开(公告)号:KR101101139B1
公开(公告)日:2012-01-05
申请号:KR1020090113282
申请日:2009-11-23
Applicant: 서강대학교산학협력단
Abstract: 본 발명은 모티브 스캔을 이용한 화질 평가방법 및 장치에 관한 것으로서, 원영상의 에지를 검출하고, 검출된 원영상의 에지를 이용하여 원영상과 및 열화 영상의 에지에 대하여 모티브 스캔을 수행한 다음, 원영상의 에지를 모티브 스캔한 결과와 열화 영상의 에지를 모티브 스캔한 결과 간의 모티브 차이값에 근거하여 화질을 평가하는 것을 특징으로 하며, 기존의 객관적인 화질 평가 방법에 의한 평가결과보다 사람이 직접 평가한 주관적인 화질평가와 더 유사하고, 평가 시간도 빠른 효과가 있다.
-
公开(公告)号:KR1020110056808A
公开(公告)日:2011-05-31
申请号:KR1020090113282
申请日:2009-11-23
Applicant: 서강대학교산학협력단
Abstract: PURPOSE: A method and apparatus for assessing an image quality are provided to assess the image quality based on the differences in motif values using a motif scan. CONSTITUTION: A motive scanning unit(120) performs motif scan about an edge portion of an original image and a deteriorated image. An image quality index generator(130) compares the motif of the edge area of the original image and deteriorated image. The image quality index generating unit creates the image quality index from a motif difference value. An image quality evaluator(140) determines the average value of the combination which has maximum value through the combination of the generated image quality evaluation index by edge direction.
Abstract translation: 目的:提供一种用于评估图像质量的方法和装置,以基于使用图案扫描的图案值的差异来评估图像质量。 构成:运动扫描单元(120)执行关于原始图像的边缘部分和劣化图像的图案扫描。 图像质量指标生成器(130)将原始图像的边缘区域的图案与劣化图像进行比较。 图像质量指标生成单元从图案差值创建图像质量指标。 图像质量评估器(140)通过边缘方向上生成的图像质量评估指标的组合来确定具有最大值的组合的平均值。
-
-
-
-