A new method for unsupervised segmentation of color-texture regions in imag
es and video is presented. This method, which we refer to as JSEG, consists
of two independent steps: color quantization and spatial segmentation. In
the first step, colors in the image are quantized to several representative
classes that can be used to differentiate regions in the image. The image
pixels are then replaced by their corresponding color class labels, thus fo
rming a class-map of the image. The focus of this work is on spatial segmen
tation, where a criterion for "good" segmentation using the class-map is pr
oposed. Applying the criterion to local windows in the class-map results in
the "J-image," in which high and low values correspond to possible boundar
ies and interiors of color-texture regions. A region growing method is then
used to segment the image based on the multiscale J-images. A similar appr
oach is applied to video sequences. An additional region tracking scheme is
embedded into the region growing process to achieve consistent segmentatio
n and tracking results, even for scenes with nonrigid object motion. Experi
ments show the robustness of the JSEG algorithm on real images and video.