Color to Grayscale Transform Preserving Maximum Information

• Main Authors: Hoai-Nam Le, 黎淮南
• Other Authors: none
• Format: Others
• Language: en_US
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/19426495715898823556

碩士 === 逢甲大學 === 通訊工程所 === 98 === Color-to-gray conversion in many applications requires preserving the visual appearance and feature discrimination of color images. The existing methods are still need of improvement in this aspect. We propose two color-to-gray conversion algorithms. One is the global mapping based and the other is the local-global mapping based. The proposed methods convert accurately various categories of color images to grayscale images, including natural images, computational images, and painting images. The global mapping scheme is simple and fast, yet it preserves feature discrimination and appropriate color order of color images. The local-global mapping scheme not only retains the visual appearance of the color image but also compensates the global mapping method for possible loss of color information. Experimental results show that the proposed methods produced perceptually accurate and preferred images when they were compared with other schemes.