Conference Paper

A texture recognition coloring technique for natural gray images

Menoufia Univ., Shibin el Kom
DOI: 10.1109/ICCES.2007.4447054 Conference: Computer Engineering & Systems, 2007. ICCES '07. International Conference on
Source: IEEE Xplore

ABSTRACT Gray image coloring is utilized to increase the visual appeal of images such as old black and white photos, movies or scientific illustrations. Most of authors working in coloring of gray scale images have used primitive methods for coloring which are both inaccurate and limited. In this paper we propose a new technique for computer coloring gray scale images. This technique works for texture based images like natural scenes. It's based on segmenting the image into different regions according to their textures. Real colors of the image can then be obtained by classifying these textures to predefined texture classes. Recognition of these textures is performed by matching these textures with a training set stored in a special database. We validate the efficiency of our coloring system by coloring several sets of natural gray images with high quality real colors.

Download full-text


Available from: Noura Abd El-Moez Semary, Sep 26, 2015
145 Reads
  • Source
    • "One of the problems of colorization is how to select the suitable colors, mainly the original colors, to generate a colored image similar to the original color one. Different colorization methods treats this problem in the literature, most of these trials are covered and discussed in our previous publications [10] [11]. One of the common colorization methods is Anat technique [7] where the user draws some scribbles on a gray image using a color palette and a brush like tool, then the computer colorizes the image using optimization depending on the fact, the nearby pixels in gray should have the same color. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Image colorization is a new image processing topic which refers to recolor gray images to look like the original color images as possible. Different methods appeared in the literature to solve this problem, the way which leads to thinking about decolorization which means eliminating the colors of color images to just small color keys, aid in the colorization process. Due to this idea, decolorization is considered as a color image encoding mechanism. In this paper we propose a new decolorization system depends on extracting the color seeds using morphology operations. Different decolorization methods was studied and compared to our system results using different quality metrics.
  • Source
    • "And the trends for coloring were appeared from 80s. We have classified these trends into three categories: Hand coloring, Semi automatic coloring, and automatic coloring in our previous publications [1] [2] [3] [4]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Since the human visual system is sensitive to colors rather than gray shades, we aim to emphasize the appearance of black and white movies and recolor them to obtain near natural colored movies that look like their original colors. The goal of our research is to implement a powerful automatic coloring system that is suitable for coloring movies with high quality colors and in fast time as possible. Our proposed system based on colorizing the movie shot by shot rather than frame by frame, so that different techniques are presented like shot cut detection, motion estimation, similarity features between images and colorization. By this paper we have succeeded to propose and implement a complete automatic colorization system specified for movies and we nearly achieve our goals.
    Informatics and Systems (INFOS), 2010 The 7th International Conference on; 04/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Colorization is an appealing area in the world of image processing. It has been used to increase the visual appeal of images such as old black and white photos, classic movies or scientific illustrations. Also, It has been very important in color image compression and video compression. Colorization, the task of coloring a grayscale image or video, involves assigning an intensity or luminance from the single dimension to a quantity that varies in three dimensions, such as red, green, and blue channels. Different colorization techniques are prevailing like hand coloring, semi automatic coloring and automatic coloring. Hand coloring and semi automatic coloring require intensive and perfect human interference. We are introducing a methodology for adding color to grayscale images in a way that is automatic and require little execution time. Towards this aim, a colorful image of the similar content as the grayscale image is taken, as an input source image by means of different image retrieval techniques. Then, the best matching source pixel is determined using luminance matching technique, for each pixel of the target grayscale image. Once a best matching source pixel is found, its chromaticity values are assigned to the target pixel while the original luminance value of the target pixel is retained.
    2013 Nirma University International Conference on Engineering (NUiCONE); 11/2013

Questions & Answers about this publication

  • Noura Abd El-Moez Semary added an answer in Image Processing:
    How can I texture segmentation using wavelet transform?
    I have completed texture classification using wavelet transform. I want to accomplish texture segmentation using the same technique. I am confused how to start.
    Noura Abd El-Moez Semary
    Check my publications,

    Gray image coloring using texture similarity measures

    A texture recognition coloring technique for natural gray images
    • Source
      [Show abstract] [Hide abstract]
      ABSTRACT: The trend for coloring gray scale mages becomes very interesting research point nowadays since it is utilized to increase the visual appeal of images such as old black and white photos, movies or scientific illustrations, and different techniques for doing that exist in the literature. There are many traditional ways for coloring like hand-coloring and pseudocoloring, but the trend for automatic computer based coloring is an important goal for many researchers in this field. From our side of view all these trials are still depend on human interaction in the coloring process. In this thesis, we propose a new system for automatic gray image coloring. The proposed system is constructed of texture based recognition system that recognizes the objects in textural images like natural scenes, and then retrieve their actual colors from a previous knowledge about their classes. This procedure is a trial of simulating the human vision in this area. The proposed Texture Recognition based Image Coloring System (TRICKS) is composite of three stages; segmentation stage to segment the image into different regions according to their textural characteristics, classification stage to classify or recognize each region to be one of a predefined set of texture classes. For each class, a hue color is attached which is transferred to the regions of this class in the final stage, the coloring stage. This thesis is a research work for studying different gray image features, segmentation and classification techniques, and different color modes to select the suitable techniques for achieving the best coloring results.
      01/2007, Degree: Master, Supervisor: Mohyi.M.Hadhoud,Wail.S.El Kilani & Nabil.A.Ismail

    + 1 more attachment