Image Visual Improvement on Handheld Devices Using Linear Mapping Function

Image Visual Improvement on Handheld Devices Using Linear Mapping Function

Balakrishnan Natarajan, Shantharajah Periyasamy, Shrinivas S.G.
Copyright: © 2017 |Pages: 6
DOI: 10.4018/IJHCR.2017100105
(Individual Articles)
No Current Special Offers


In the current scenario, handheld devices play a major role in the human life. Handheld devices become an essential kit, not only acting as a conduit for social media, but also in medicine. Several new opportunities for the different applications of mobile image processing exist, such as to improve the visual quality, and image recognition. Captured images do not provide an effective visualization due to the poor specifications of the device camera, low light, poor sensing features, etc. In this article, an adaptive histogram equalization for contrast enhancement using a linear mapping function scheme is proposed to improve the images. The image from the mobile device is fed into a contrast improvement phase. The intensity value of each pixel is processed to improve the image visuals. The pixel density value is measured and according to it, the low-density value is changed. Hence, the image is tuned finely to yield better results.
Article Preview

1. Introduction

The handheld devices have become an essential tool in human part of life. Advancement in the computer technology has leaded the user with reduced size, weight, costs with faster monitoring and communications. Now a day, image access on the handheld devices becomes very much familiar among the users. Image Processing is the type of signal processing in which the input can be any photograph and / or video frame with the features extracted images. Image processing is technique which transfers the image into a digital form and presents in a design as the user required form like improving the image or extracting the useful information.

The image processing application includes medical imaging, Image sharpening and restoration, transmission and encoding, remote sensing, etc. Images with poor contrast fail to provide an effective result while performing operations on it. In many circumstances the imaging device are unpleasant at the time of capturing. The result yields poor quality image. Further, the image finds its visual quality based on the capability and functionality of device. The images have poor illumination conditions, low quality image sensors and errors of the image while capturing leads to poor contrast image. Because of this the users are unable visualize the images.

The contrast of the image is less because of the poor illumination conditions, low quality image sensors, errors on the images, etc. Generally, contrast development method can be categorized as context-sensitive method and context-free method. The contrast is defined using the rate of change in intensity between adjacent pixels is referred as context-sensitive method and if the contrast is changed pixel by pixel in signal form is referred as context-free method.

Handheld devices have enormously developed in the recent years in the area like agriculture, medicine, Learning system, remote sensing and lot more. Further, these devices are integrated as a part of human life. The characters in these devices have higher usability compared to the large display technologies. The information is accessed with the screen space restrictions. Only little information can be seen at a time and it is required for the users to navigate through the certain options. Further, the images captured by these devices cannot assure for its quality. The quality of the image depends on several factors like low light, poor sensing features, etc.

The images that are captured with low contrast are unsuitable of human predictions. Some of the examples are Medical data and Industrial image data. There are many contrast enhancement algorithms available. Among them Histogram Equalization is simple and easy to implement. Generally, Histogram Equalization can be categorized as Global Histogram Equalization (GHE) and Local Histogram Equalization (LHE) or Adaptive Histogram Equalization (AHE). In GHE entire histogram of the image is considered as the input, and then further processing is done. This method leads to the loss of contrast in some regions. But in LHE firstly the region is defined, and then the histogram is obtained. Each pixel of the entire image is processed accordingly. Hence, the computation complexity becomes higher. The nonlinear contrast enhancement produces the histogram with uniform density of pixels along its axis. This contrast enhancement has more brightness values in the original image. The uniform distribution strongly saturates the brightness values at the light and dark tails of the original histogram. The Gaussian stretch is one of the nonlinear stretches which enhance the contrast in the tail region of the histogram. This stretch limits to 0 to 255 that makes the improvement on the light and dark ranges of the image.

This paper proposes a new scheme that improves the contrast of the image by working of the different levels of intensity values. Further, the Linear Mapping function is used to map the pixels to enhance the contrast. Section 2 describes the related work; Section 3 describes the Histogram Equalization, Section 4 proposes the Adaptive Histogram Equalization for contrast Enhancement using Linear Mapping function that improves the images and finally, Section 4 concludes the activity.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing