Camouflage, also called as cryptic coloration, is a defense mechanism or tactic that organisms use to disguise their appearance, usually to blend in with their surroundings. Camouflage is used to mask their location, identity and movement. Detecting camouflaged moving foreground objects has been known to be difficult due to the similarity between the foreground objects and the background. Methods present to detect camouflage image i.e., decamouflaged techniques are i. Visual camouflaged

more »

... , ii. Co-occurrence matrix and invariant central moments, iii. Color and intensity based camouflaged detection, iv. Use of GLCM (gray level co-occurrence matrix) and dendrogram in camouflage detection, v. Color, edge and intensity-based background subtraction, vi. HSV (hue, saturation, value) color and GLCM texture to identify camouflaged object, vii.3D convexity-based camouflage detection method. In this paper we present a fusion framework to address this problem in wavelet domain. The proposed fusion framework is denoted by "FWFC" (fusion in the wavelet domain for foreground detection in camouflaged senses). We first show that the small differences in the image domain can be highlighted in certain wavelet bands. Then each wavelet coefficient of foreground is estimated by formulating foreground and background models for each wavelet band. The proposed fusion framework works on/from different wavelet bands based on the characteristics of the wavelet transform. In the field of military security and medical field (e.g.: drugresistant tuberculosis) this fusion framework can have many applications. This method has shown the significant performance which is better than the existing methods in terms of the camouflaged foreground detection.