Image Analysis and Computer Vision: 1997

Rosenfeld, Azriel

doi:10.1006/cviu.1998.0697

Cited by 8 publications

(3 citation statements)

References 772 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Descriptions of the general approaches taken in the development of the specific algorithms can be found in the texts of Marr [3], Pratt [4], and Zhou and Chellappa [5]. A recent bibliography has been prepared by Rosenfeld [6]. As will be seen in the historical evolution, early measurements discovered that target boundary estimation techniques were not robust because they exhibited sensitivity to noise, aspect, target variation, and partial obscuration.…”

Section: ----------------mentioning

confidence: 99%

Aided and automatic target recognition based upon sensory inputs from image forming systems

Ratches

Walters

Buser

et al. 1997

IEEE Trans. Pattern Anal. Machine Intell.

101

View full text Add to dashboard Cite

Abstract-This paper systematically reviews 10 years of research that several Army Laboratories conducted in object recognition algorithms, processors, and evaluation techniques. In the military, object recognition is applied to the discrimination of military targets, ranging from human-aided to autonomous operations, and is called Automatic Target Recognition (ATR). The research described here has been concentrated in human-aided target recognition applications, but some attention has been paid to automatic processes. Definitions and performance metrics that have been developed are described along with performance data showing the present state-of-the-art. The effects of signal-to-noise and clutter parameters are indicated in the data. Multisensor fusion and model-based algorithms are discussed as the latest techniques under consideration by the military research community. The results demonstrate that useful performance can be achieved, and tools are evolving to understand and improve the performance under real-world conditions. The referenced research strongly indicates the need for the development of image science, as described in the paper, to support the theoretical underpinnings of ATR.

show abstract

Section: ----------------mentioning

confidence: 99%

Aided and automatic target recognition based upon sensory inputs from image forming systems

Ratches

Walters

Buser

et al. 1997

IEEE Trans. Pattern Anal. Machine Intell.

101

View full text Add to dashboard Cite

show abstract

“…(A.2) Books [46][47][48][49][50][51][52]; a new journal [53]; journal special issues [54][55][56][57][58]; papers on research at specific institutions [59][60][61][62][63][64][65][66][67][68][69][70][71][72][73][74][75][76]; and the previous bibliography in this series [77].…”

Section: A Introductionmentioning

confidence: 99%

Image Analysis and Computer Vision: 1998

Rosenfeld

1999

Computer Vision and Image Understanding

Self Cite

View full text Add to dashboard Cite

This paper presents a bibliography of over 2250 references related to computer vision and image analysis, arranged by subject matter. The topics covered include computational techniques; feature detection and segmentation; image and scene analysis; two-dimensional shape; pattern; color and texture; matching and stereo; three-dimensional recovery and analysis; three-dimensional shape; and motion. A few references are also given on related topics, including geometry and graphics, compression and processing, sensors and optics, visual perception, neural networks, artificial intelligence and pattern recognition, as well as on applications.

show abstract

“…There is extensive literature on segmentation and no review of the literature is possible within the limitations of this article. As examples we mention Charalampidis and Kasparis (2002), Malik et al (2001), Minotte et al (2000), Rosenfeld (2000), Rezaee et al (2000), and Shi and Malik (2000), where different methods are employed for identifying regions and their boundaries to achieve segmentation. Most approaches are based on intensity and proximity analysis and are computationally intensive.…”

mentioning

confidence: 99%

Image segmentation via local higher order statistics

Farhadi

2003

Int J Imaging Syst Tech

View full text Add to dashboard Cite

ABSTRACT:The aim of this work is to present a method for the segmentation of images based on local higher order statistics. The algorithm can be applied for the separation of objects from a texture background and the segmentation of textures. Key words: image processing; computer vision; higher order statistics; image classification and detection; texture discriminants; segmentation I. INTRODUCTIONThis article is a continuation of Shahshahani (2001, 2002), where some methods for the classification of images and locating objects within images were presented. The methods of Farhadi and Shahshahani are refined here in several ways. The key differentiation method of Farhadi and Shahshahani was based on examining certain curves reflecting local second and higher order statistics of the image. Here we extract information from the statistical invariants by using discrete cosine transform and construct new scatter plots and investigate their geometric properties. The information is used to obtain segmentation of images. There is extensive literature on segmentation and no review of the literature is possible within the limitations of this article. As examples we mention Charalampidis and Kasparis (2002), Malik et al. (2001), Minotte et al. (2000), Rosenfeld (2000), Rezaee et al. (2000), and Shi and Malik (2000), where different methods are employed for identifying regions and their boundaries to achieve segmentation. Most approaches are based on intensity and proximity analysis and are computationally intensive. In some approaches one makes use of a data bank or training to identify the boundaries of desired regions. Here we rely exclusively on local statistical analysis of the data and the results, as demonstrated in the article, are promising. Needless to say one can make improvements on the performance by a judicious use of a data bank. The complexity of our proposed algorithms is O(ᏺ), and therefore its implementation is practical.

show abstract

Image Analysis and Computer Vision: 1997

Cited by 8 publications

References 772 publications

Aided and automatic target recognition based upon sensory inputs from image forming systems

Aided and automatic target recognition based upon sensory inputs from image forming systems

Image Analysis and Computer Vision: 1998

Image segmentation via local higher order statistics

Contact Info

Product

Resources

About