Project:  Peer Group Filtering and Perceptual Color Quantization


Y. Deng, Charles Kenney, B.S. Manjunath

In the first part of this work, peer group filtering (PGF), a nonlinear algorithm for image smoothing and impulse noise removal in color images is presented. The algorithm replaces each image pixel with the weighted average of its peer group members which are classified based on the color similarity of its neighboring pixels. Results show that it effectively removes the noise and smoothes the color images without blurring the edges and the details. In the second part of the work, PGF is used as a preprocessing before color quantization. Local statistics obtained after PGF are used as weights in the quantization to suppress color clusters in the noisy regions, since human perception is less sensitive to the differences in these areas. As a result, very coarse quantization can be obtained while preserving the color information in the original images. This can be useful for efficient color indexing in the content based retrieval application. Also useful for color image segmentation.


Some results of PGF and color quantization are shown here. These are the color images appeared in the proceeding paper. Icon images (jpg) are shown on this page. Click on each image to see the uncompressed full-resolution one (tiff).

a) small area of the original "baboon" image

b) same area of the 5% corrupted image

c) result of vector median filtering

d) result of Teager-operator


e) result of peer group filtering.


(a) part of the original "baboon"


(b) result of PGF

(c) result of Gaussian filtering.

(a) original "baboon" image (512x512)

(b) result of PGF

(c) result of quantization with 18 colors.

"flower garden" video (352x240)

(a) original image


(b) result of PGF

(c) result of quantization with 13 colors.


These materials are presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

  1. C.Kenney, Y. Deng, B. S.Manjunath, G. Hewer, "Peer group image enhancement," IEEE Transactions on Image Processing, vol.10, (no.2), IEEE, Feb. 2001. p.326-34.  [abstract]

  2. Y. Deng, B. S. Manjunath, C. Kenney, M.S.Moore, H.Shin, " An efficient color representation for image retrieval," IEEE Transactions on Image Processing, vol.10, (no.1), IEEE, Jan. 2001. p.140-7. [abstract]

  3. Y. Deng, S.Kenney, M.S.Moore and B. S.Manjunath, "Peer group filtering and perceptual color image quantization", Proc. IEEE International Symposium on Circuits and Systems VLSI , (ISCAS'99), Orlando, FL,  vol 4, pp.21-4 , June 1999. [abstract]

Back to Image Segmentation

Home | People | Research | Publications | Courses | Seminars | Links