Image conversion

About: Image conversion is a research topic. Over the lifetime, 2490 publications have been published within this topic receiving 19077 citations.

Influence of Color-to-Gray Conversion on the Performance of Document Image Binarization: Toward a Novel Optimization Problem

Abstract: This paper presents a novel preprocessing method of color-to-gray document image conversion. In contrast to the conventional methods designed for natural images that aim to preserve the contrast between different classes in the converted gray image, the proposed conversion method reduces as much as possible the contrast (i.e., intensity variance) within the text class. It is based on learning a linear filter from a predefined data set of text and background pixels that: 1) when applied to background pixels, minimizes the output response and 2) when applied to text pixels, maximizes the output response, while minimizing the intensity variance within the text class. Our proposed method (called learning-based color-to-gray) is conceived to be used as preprocessing for document image binarization. A data set of 46 historical document images is created and used to evaluate subjectively and objectively the proposed method. The method demonstrates drastically its effectiveness and impact on the performance of state-of-the-art binarization methods. Four other Web-based image data sets are created to evaluate the scalability of the proposed method.

Image processing device

Abstract: PROBLEM TO BE SOLVED: To automatically correct, to an erect direction, a document image inputted slantingly or mirror invertedly. SOLUTION: This method is used for detecting a character read as an image at an angle differing depending on a scan direction and with mirror image inversion applied by using, for instance, a method of character recognition to erect it. By focusing on the point that the character recognition rate of such a character image is low, the character image is extracted from the scan image to detect the presence of a rotation angle and/or mirror image conversion maximizing the recognition rate, and similar rotation/mirror image conversion is applied to the original scan image to automatically correct it to the erected image. COPYRIGHT: (C)2004,JPO

Color characteristic description apparatus, color management apparatus, image conversion apparatus and color correction method

Abstract: A process is provided for developing and converting a lookup table (hereinafter called a “LUT”) composed of only characteristic points of the characteristic of a color device and having a volume smaller than that of a multidimensional LUT into a multidimensional LUT by a table development process. Image data converting means uses the multidimensional LUT to convert input image data into output image data. Thus, an effect can be obtained in that a color management apparatus can be operated with only the LUT composed of only characteristic points of the characteristic of the device and having a small volume.

Method, apparatus, system, and computer executable program for image processing

Abstract: A digital still camera produces size-reduced image data of a JPEG file, which is converted into printable image data of a TIFF file according to a converting parameter. In the digital still camera, raw image data (CCD-RAW) is produced, corresponds to the JPEG data, and has an unreduced format. Images of the JPEG data are displayed in a playback manner. A customer order of an image among the displayed images to be printed is processed. JPEG data associated with the image of the customer order is adjusted according to a standard adjusting parameter. The standard adjusting parameter is modified into a first adjusting parameter. Raw image data associated with the image of the customer order is converted into TIFF data by image conversion according to the first adjusting parameter and/or a standard converting parameter being preset.

On conversion from color to gray-scale images for face detection

Abstract: The paper presents a study on color to gray image conversion from a novel point of view: face detection. To the best knowledge of the authors, research in such a specific topic has not been conducted before. Our work reveals that the standard NTSC conversion is not optimal for face detection tasks, although it may be the best for use to display pictures on monochrome televisions. It is further found experimentally with two AdaBoost-based face detection systems that the detect rates may vary up to 10% by simply changing the parameters of the RGB to Gray conversion. On the other hand, the change has little influence on the false positive rates. Compared to the standard NTSC conversion, the detect rate with the best found parameter setting is 2.85% and 3.58% higher for the two evaluated face detection systems. Promisingly, the work suggests a new solution to the color to gray conversion. It could be extremely easy to be incorporated into most existing face detection systems for accuracy improvement without introduction of any extra cost in computational complexity.