期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2000
卷号：XXXIII Part B5/2
页码：20-27
出版社：Copernicus Publications
摘要：The task of object recognition involves classifying extracted objects, given a collection of extracted objects, eachbelonging to a predefined class. Inherently, object recognition from imagery is an ill-posed problem. Hence, additionalbehaviors or attributes of the extracted objects need to be incorporated in the analysis. In the case of color imageries,color information is one such attribute. To use the color information for the recognition, we should be able to properlyextract the “unadulterated” color information, that is the information without the biases of the image-capturing device.Hence, that is where “color image restoration” comes into the picture. Color image restoration involves recovering colorinformation that has been degraded during image formation. In other words, restoration purifies the adulterated colorinformation. After initial stages of preprocessing, the next step towards recognition of objects is image segmentation. Inthis research, multilevel threshold and adaptive threshold techniques have been applied to color images in different colordomains. The results have been tabulated and compared. This comparison is found to be very useful for selecting thesuitable technique for the application at hand.
