Prasant Kumar Mahapatra

A hybrid particle swarm optimization and artificial immune system algorithm for image enhancement

Image enhancement means to improve the perception of information in images. Histogram equalization (HE) and linear contrast stretching (LCS) are the commonly used methods for image enhancement. But images obtained through these processes, generally, have excessive contrast enhancement due to which they are not suitable for use in fields where brightness is of critical importance. In this paper, a hybrid algorithm based on Particle Swarm Optimization (PSO) along with Negative Selection Algorithm, a model of artificial immune system, is proposed for image enhancement which is achieved by enhancing the intensity of the gray levels of the images. The proposed algorithm is applied to histogram equalized images of lathe tool and MATLAB inbuilt images to verify its effectiveness. The results are compared with conventional enhancement techniques such as HE, LCS and Standard PSO algorithm based image enhancement.

A social spider optimized image fusion approach for contrast enhancement and brightness preservation

Display Omitted A social spider optimized image fusion approach is proposed for image enhancement.The resultant enhanced image has an optimal trade-off between sharpness and noise.Performance and robustness of the proposed method is tested, and validated the results with well-known algorithms.The proposed method may be easily extended to other applications. Image enhancement means to process the image in order to obtain a visually pleasing effect on image with more perception details and less noise output. In this work, a social spider optimization based algorithm is used to produce two enhanced images, one having high sharpness or contrast with maximum entropy and the other having high peak signal-to-noise ratio (PSNR) sharp image. The two enhanced images are fused to obtain an output image which has an optimal trade-off between sharpness and noise. The proposed algorithms are applied to lathe tool images as well as to some other standard images to verify their effectiveness. The results are compared with conventional image enhancement techniques such as Histogram Equalization (HE), Linear Contrast Stretching (LCS), and Standard Particle Swarm Optimization (PSO) algorithm.

Improved thresholding based on negative selection algorithm (NSA)

Thresholding is a tool of image segmentation which groups the pixels in a logical way. In this paper, a novel algorithm based on negative selection algorithm a model of artificial immune system is proposed for image thresholding. The proposed algorithm is applied on the thresholded images of lathe tool produced using maximum information entropy (MIE) and global thresholding based technique resulting in an improved image. To verify the algorithm and results, it has also been applied on some of the inbuilt MATLAB (MATrix LABoratory) images. Histogram is employed to analyze the results. Further, the results of improved algorithm are compared with the results of MIE and the global thresholding methods to check the effectiveness of the proposed method. The experimental results confirm the potential of the developed algorithm.

Modified Cuckoo Search-Based Image Enhancement

Swarm intelligence-based evolutionary algorithms have a prominent role in the field of automatic image enhancement that is considered as the optimization problem. In this paper, a modified cuckoo search-based image enhancement is proposed. The modified cuckoo search is used to find the optimal solution of the problem automatically. The proposed method is applied to the lathe tools and some other standard images for improvement of contrast and brightness. The results of the proposed image enhancement method are compared with the other conventional image enhancement techniques like histogram equalization (HE), linear contrast stretching (LCS) and particle swarm optimization (PSO).

A Machine Vision System for Tool Positioning and Its Verification

This paper presents a machine vision–based precise tool positioning and verification system that may be used with milling and lathe machines, and so on. For many industrial applications, the accuracy required in machining operations is of the order of microns. The developed machine vision–based tool position verification process involves pixel calibration to compute and measure real-world minute dimensions. These measurements are based on two-dimensional spatial correlation of sequential images captured from the movement of the tool with a resolution of 250 µm. The captured sequential images are thresholded using a new bio-inspired technique named Negative Selection Algorithm, a model of Artificial Immune System. The developed system extracts the difference between the actual and target positions of the tool from the captured images through image processing and calculates the error. To compensate for the positional error, alignment commands are fed to the two-axis high precision motor. The maximum error observed was ±206 µm for 14.99999 mm movement.

Artificial Immune System Based Image Enhancement Technique

Artificial immune system (AIS) inspired by immune system of vertebrates can be used for solving optimization problem. In this paper, image enhancement is considered as a problem of optimization and AIS is used to solve and find the optimal solution of this problem. Here, image enhancement is done by enhancing the pixel intensities of the images through a parameterized transformation function. The main task is to achieve the best enhanced image with the help of AIS by optimizing the parameters. The results have proved better when compared with other standard enhancement techniques like Histogram equalization (HE) and Linear Contrast Stretching (LCS).

Image thresholding based on swarm intelligence technique for image segmentation

Image thresholding is a critical task of image segmentation. Selection of the optimal value of the threshold is the most important task for image thresholding. The better the value of threshold better is the quality of segmentation. In this paper, recent swarm intelligence technique (fireworks algorithm) has been used for image thresholding. Fireworks algorithm is used to maximize two functions, namely Kapur and Otsu. Results show that quality of segmentation is better in case of Firewok-Otsu than Firework-Kapur. Comparison of results has been done on the basis of PSNR value.

A Hybrid of Fireworks and Harmony Search Algorithm for Multilevel Image Thresholding

Multilevel image thresholding is an essential part of image processing. This paper presents a hybrid implementation of fireworks and harmony search algorithm where Kapur’s entropy is used as the fitness function for solving the problem. The results of the proposed method have been compared with the standard fireworks algorithm (FWA) and particle swarm optimization (PSO) based multilevel thresholding methods. Experimental results indicate that the proposed method is a promising approach in the field of image segmentation.

Tool condition monitoring using the chain code technique, pixel matching and morphological operations

Tool condition in various machining processes directly affects the quality of machined surfaces. Tool condition needs to be monitored with the purpose of evaluating the tool life and timely replacing it, if it is not in favourable condition. The present work focuses on monitoring of tool condition through image processing. The images of the single point lathe tool have been captured before and after machining by a machine vision system. These images are processed using MATLAB image processing toolbox software and tool condition has been evaluated. Different methods, i.e. Chain code, pixel matching and morphological operations have been successfully implemented for extracting the shape of the tool. Depending upon the shape of the tool, it has been classified as ‘Normal’ or ‘Worn’.

Real-time stereo generation for surgical vision during minimal invasive robotic surgery

This paper proposes a framework for 3D surgical vision for minimal invasive robotic surgery. It presents an approach for generating the three dimensional view of the in-vivo live surgical procedures from two images captured by very small sized, full resolution camera sensor rig. A pre-processing scheme is employed to enhance the image quality and equalizing the color profile of two images. Polarized Projection using interlacing two images give a smooth and strain free three dimensional view. The algorithm runs in real time with good speed at full HD resolution.