Entropic thresholding

Pal, Nikhil R.; Pal, Sankar K.

doi:10.1016/0165-1684(89)90090-x

Cited by 274 publications

(147 citation statements)

References 6 publications

Supporting

Mentioning

142

Contrasting

Unclassified

Order By: Relevance

“…For example, the one defined by Beaubouef et al (1999) is applicable to relational database and the one of Düntsch and Gediga (1998) for optimal granulation and feature selection. Reports are also available on image entropy measures and object extraction where image entropy is defined based on both histogram (Pun, 1981) and co-occurrence matrix (Pal and Pal, 1989) making use of the global and local information of image. Use of logarithmic and exponential gain functions in this regard is explained in (Pal and Pal, 1991).…”

Section: Discussionmentioning

confidence: 99%

Granular computing, rough entropy and object extraction

Pal

Shankar

Mitra

2005

Pattern Recognition Letters

159

View full text Add to dashboard Cite

The problem of image object extraction in the framework of rough sets and granular computing is addressed. A measure called ''rough entropy of image'' is defined based on the concept of image granules. Its maximization results in minimization of roughness in both object and background regions; thereby determining the threshold of partitioning. Methods of selecting the appropriate granule size and efficient computation of rough entropy are described.

show abstract

Section: Discussionmentioning

confidence: 99%

Granular computing, rough entropy and object extraction

Pal

Shankar

Mitra

2005

Pattern Recognition Letters

159

View full text Add to dashboard Cite

show abstract

“…and C(i, j) the frequency of occurrence of th~ gray level i followed by j, i.e., C is the cooceurrenee matrix [5). Lei f and g be two functions such that ( 10) …”

Section: Correlation Using Local Informationmentioning

confidence: 99%

“…It can be done by gray-level thresholding as well as by pixel classification (region growing). There exist a numb<:r of approaches (both classical-and fuzzy-mathematical) to the problem [1, [5][6][7][8], A recent fuuy set-theoretic algorithm [7J used both gray-level ambiguily and fuzzy compact ness measures in order to take inlo account global HlId spatial informacion about an image. It provides fuzzy (and non fuzzy as a special case) segmenced output in order to avoid committing oneself to a specific thresholding for ill-defined input regions.…”

Section: Introductionmentioning

confidence: 99%

Image segmentation using fuzzy correlation

Pal

Ghosh

1992

Information Sciences

View full text Add to dashboard Cite

AOSTKACTA concept or correlation between twO properties (fuzzy repre~cnlations) of an image IS introduced. A sel of algorithms for image segmenLation (both fuvy and nonfuzzy) has been formulated. The spatial infonnation is taken care of by the following measures: transitional correlation and within-class correlation, A relation between the correlation coefficient and thc inde~ of fuzziness is theoretically eSLablished and e~perimenlally verified, The effective ness of the algorithms is illustrated on images having different types of hiSlOgrams.

show abstract

“…Section 3 introduces the concept of relative entropy and presents a relative entropy-based thresholding algorithm. In Section 4, experiments are conducted based on various test images in comparison to the local entropy and joint entropy methods described in reference (1). Finally a brief conclusion is given in Section 5.…”

Section: Introductionmentioning

confidence: 99%

“…A widely used co-occurrence matrix is an asymmetric matrix which only considers the grey level transitions between two adjacent pixels, horizontally right and vertically below. ~l) More specifically, let tij be the (i,j)th entry of the co-occurrence matrix T. Following the definition in reference (1),…”

Section: Introductionmentioning

confidence: 99%