Mathematical morphology operations with a comparator array processor

ABSTACT Image segmentation has been an important and challenging issue in the field of computer vision over decades. It plays a critical role for most image analysis tasks, such as object detection and recognition. The aim of this paper is to obtain segmented image of Printed Circuit Board (PCB)’s track using mathematical morphological operation. Morphological image analysis is based on the idea that images represent a collection of spatial patterns that can be analyzed based on some predefined patterns called structuring elements. Most basic morphological operation, dilation and erosion have been employed in this research. Detail elaboration on this method will be discussed and experimental results are presented.

A novel method of the active contour model is proposed by introducing the mathematical morphological operations on the "contour object", which is a binary image object whose outline is the contour. The contours are shrunk and expanded by simply applying the mathematical morphological operations on the contour objects. The split and fusion of contour are also carried out by the mathematical morphological operations, and no additional procedure for split or fusion is required.

An optoelectronic model of discrete time cellular neural networks (DTCNN) is presented. Connections between cells and parallel input-output are realized using optoelectronic devices. As an emitter-receiver device an optical thyristor is applied. Connections between cells are realized by diffractive Damman gratings. We propose a dual rail system for early processing of binary images. The CNN system performs mathematical morphology and space logic operations.

Morphology is an image algebra technique whereby the shape and structure of an input object is transformed by a smaller object called the structuring element. The two most fundamental morphological operations, erosion and dilation, are usually defined in terms of set operations. Alternatively they can be understood in terms of a convolution followed by a threshold. In this paper we describe an iterative acoustooptic (AO) morphological image processor. The input to the system is displayed on a 128 × 128 magnetooptic spatial light modulator, and the system utilizes an AO Bragg cell in the Fourier plane of a coherent optical correlator to generate the desired structuring element. Thresholding is performed electronically in an image processing system. The feedback necessary for multiple erosions and dilations is provided electronically via a single computer that controls both an image processing system in the output image plane and the MOSLM.

Image segmentation refers to the process of partitioning a digital image into multiple sets of pixels are known as segments. The main goal of image segmentation is to change and simplify the representation of an image into something that is more meaningful and easier to analyze. The manual transactions for segmentation by experts is a difficult phenomena and time consuming process as well as. Most of the images in the process received are lacking of good quality. The main objective of this study is to develop a reliable mechanism to enhance the image quality and extract the abnormal portion through brain MR image accurately. A spatial filter is designed by utilizing the spatial information of the image and further to use collective information to enhance the poor quality of image(s), whereas, k-means clustering and mathematical morphological operations which extract the tumor segment from images. The proposed method is applied on different types of brain MR images for both visual and quantitative evaluations. Experimental results concluded during the practicum showed promising and reliable accuracy to open a thorough research for better future perspective of the technique developed in the article. Fully Automatic Detections of Abnormalities of Brain MR Images by utilizing Spatial Information and Mathematical Morphological Operators. Available from: http://www.researchgate.net/publication/265294217_Fully_Automatic_Detections_of_Abnormalities_of_Brain_MR_Images_by_utilizing_Spatial_Information_and_Mathematical_Morphological_Operators [accessed Nov 3, 2015].

Morphological openings and closings are basic operators in mathematical morphology. Morphological area openings and area closings have the same functions as standard morphological openings and closings but avoid distorting object boundaries. The conventional implementation of morphological area operators is based on the heap data structure. A new methodology for implementing morphological area operators, which relies on the disjoint set data structure, is proposed in this paper. The computational complexity of our method is O(N) where N is the image size, and not related to the area parameter. Experiments show that the new implementation of grayscale area operators runs faster than the conventional implementations. The computational complexity of binary area operators is also studied in this paper.

Mathematical morphological operations are commonly used as a tool in image processing for extracting image components that are useful in the representation and description of region shape. In this paper, six basic morphological operations are investigated to remove noise and enhance the appearance of binary images. Dilation, erosion, opening, closing, fill and majority operations are tested on twenty-five images and subjectively evaluated based on perceived quality of the enhanced images. Results of the experiments showed that noise can be effectively removed from binary images using combinations of erode-dilate operations. Also, the binary images are significantly enhanced using combinations of majority-close operations.

In this paper we propose definitions of distances to bipolar information. This notion is important to find a solution that matches bipolar queries, to exhibit recommendations satisfying preferences of an agent while respecting her constraints, to find an agreement between several agents. All these situations require to be able to compare candidate solutions, via their distance to some bipolar information, and several evaluation measures are proposed as well. We base distances and their comparison on mathematical morphology operators, in particular dilations and skeleton by influence zones.

This paper describes the development of an automatic segmentation method and a novel navigation system that detect polyps using advanced image processing techniques. The segmentation method described here outlines the colon wall of the CT data set of abdomen by combining the active contouring model - level set method and the minima detection using mathematical morphology theory. The polyp detection is achieved by analysing the surface curvature and the texture information surrounded on the colon wall. As such, the polyp candidates are examined not only by their shape, size but also by their texture appearance which improves the current existing methods. The major contribution of our method is the detailed information analysis using the active contour model assisted by mathematical morphology operations and texture analysis.

Visual secret sharing (VSS) is one of the cryptographic techniques of Image secret sharing scheme (ISSS) that performs encoding of secret message image (text or picture) into noise like black and white images, which are called as shares. Shares are stacked together and secret message image is decoded using human visual system. One of the major drawbacks of this scheme is its poor contrast of the recovered image, which improves if computational device is available while decoding. In this paper, we propose to improve poor contrast of classical VSS schemes for text or alphanumeric secret messages and low entropy images. Initially, stacked image is binarized using dynamic threshold value. A mathematical morphological operation is applied on the stacked image to enhance contrast of the reconstructed image. Moreover, a method is proposed that allows the size of the structuring element to change according to the contrast and the size of a stacked image. We perform experiments for different types of VSS schemes, different share patterns, different share types (rectangle and circle), and low entropy images. Experimental results demonstrate the efficacy of the proposed scheme.

A recognition algorithm for a type of coded target widely used in photogrammetry is presented in this paper. An efficient feature vector is first proposed to describe the targets, then mathematical morphological operations are used for clustering to location the the targets in the image. Finally, by ellipse fitting, each coded target in the image is recognized. Experimental results in both the better and worse case demonstrate the effectiveness of our approach.

International audience

This paper presents a novel application of mathematical morphology for Radar ELINT signals. The 1-D weak radar signals are transformed into 2-D time-frequency representation through the application of short-time Fourier Transforms (STFT). The time-frequency representation of these signals is treated as 2-D objects similar to images. Mathematical morphological operations are performed on this representation of the radar signals and are viewed as detectors. These Morphological detectors are found to be versatile in detecting weak radar signals.

The number plate recognition (NPR) system is one of the categories of smart transportation and detection mechanism (STDM). This is a combination of the technology in which the application enables the system to detect and automatically read the license id of number plate of vehicle from digitally captured images. Automatically capturing the license plate is the process of detecting and transforming the pixels data of a digital image into the plain text data or ASCII text of the number plate. Our project contains a method for the vehicle number plate recognition from the image using mathematical morphological operations (erosion, dilation). The main objective is to use and combine different morphological operations in such a way that the license plate of the certain vehicle can be detected and translatedeffectively. This is based on various operation such as image improvement, Gray scale transformation, Bilateral Filtering edge detection and getting the number plate from the picture of vehicle. After the completion of the above-mentioned steps, now the process of segmentation is being applied to detect the text present on number plate by making use ofmatching of template and OCR. This system is able to detect the license number accurately as well as quickly from the vehicle’s picture.

The exploration of the features presented by the training sets of each class (size, shape and orientation) in order to construct the respective decision regions borders without making explicitly any statistical hypothesis is presented in this paper. Its incorporation allows defining more correct decision borders since there is a significant improvement in the classification rates obtained. Mathematical morphology operators are preferentially used in this methodology, which is illustrated with two spectral features (wetness' tasselled cap and NDVI's vegetation index) of seven land cover classes constructed from Landsat TM satellite images of central Portugal.