Neuro-visually inspired figure-ground segregation

Ghosh, Kuntal; Roy, Anirban

doi:10.1109/iciip.2011.6108932

Cited by 9 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This loss should not affect the recognition accuracy. A new neuro-visual perception based figure-ground segregation claims preservation of important image information ( [10], [2]), which appears to be an appropriate tool in our problem. The entropy measure of the binary image formed by NFGS is much higher that the binary images formed by other classical binarization algorithms like Otsu's method and k-means method [2].…”

Section: Keypoint Descriptormentioning

confidence: 99%

“…A new neuro-visual perception based figure-ground segregation claims preservation of important image information ( [10], [2]), which appears to be an appropriate tool in our problem. The entropy measure of the binary image formed by NFGS is much higher that the binary images formed by other classical binarization algorithms like Otsu's method and k-means method [2]. This is because, when our eyes try to represent any object into our brain, its initial task is to segregate the object of interest from the rest of the objects of non-interest present in the scene in the form of a raw primal sketch [11].…”

Section: Keypoint Descriptormentioning

confidence: 99%

“…The paper is organized as follows. In section 2, the new neuro-visual model of figureground segregation (NFGS) is presented [2]. In the 3 rd section of the present paper the famous algorithm of Scale Invariant Feature Transform (SIFT), proposed by Lowe [3], [4] is discussed briefly.…”

Section: Introductionmentioning

confidence: 99%

“…Such modulation, termed as the extended/extra classical receptive field (ECRF), is known to elicit nonlinear responses. Based on this concept of ECRF, Ghosh et al proposed a neuro-visual model of figure ground segregation and has modified in the form of a new digital mask ( [8], [2]) as shown in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Enhancing face matching in a suitable binary environment

Das

Ghosh

2011

2011 International Conference on Image Information Processing

Self Cite

View full text Add to dashboard Cite

Computerized human face recognition is a complex task of deformable pattern recognition. The principal source of complexities lies in the significant inter-class overlapping of faces due to the variations caused by different poses, illuminations, and expressions (PIE). The popularly used computerized face recognition algorithms like PCA, EBGM etc. are fairly reliable to determine facial attributes from an image. But, in most of the cases the features are extracted in terms of gray textures. When the database size is tuned to millions, then huge processing time is required, as each of the pixel must be represented using at least eight bits. In the present paper, our objective is to minimize the processing time by reducing the number of bits to represent each pixel. This we have done by combining two methods. The first one is a neuro-visually inspired method of figure-ground segregation (NFGS) which can convert the entire face image into a binary 2D array, efficiently. The second one is the scale invariant feature transform (SIFT) which extracts the scale invariant and rotation invariant features from the binarized face image and thereafter matches the features. The proposed algorithm is found successful in actually enhancing the performance of face matching. Psycho-visual experiments also corroborate the fact.

show abstract

Section: Keypoint Descriptormentioning

confidence: 99%