Siti Norul Huda Sheikh Abdullah

License Plate Recognition using Multi-cluster and Multilayer Neural Networks

Vehicle license plate recognition has been a much studied research area in many countries. Due to the different types of license plates being used, the requirement of an automatic license plate recognition system is rather different for each country. In this paper, an automatic license plate recognition system is proposed for Malaysian vehicles with standard license plates based on image processing, feature extraction and neural networks. The image-processing library is developed in-house which we referred to as Vision System Development Platform (VSDP). Multi-cluster approach is applied to locate the license plate at the right position while Kirsch Edge feature extraction technique is used to extract features from the license plates characters which are then used as inputs to the neural network classifier. The neural network model is the standard multilayered perceptron trained using the back-propagation algorithm. The prototyped system has an accuracy of more than 91% however, suggestions to further improve the system are discussed in this paper based on the analysis of the error

Investigation on Image Processing Techniques for Diagnosing Paddy Diseases

The main objective of this research is to develop a prototype system for diagnosing paddy diseases, which are Blast Disease (BD), Brown-Spot Disease (BSD), and Narrow Brown-Spot Disease (NBSD). This paper concentrates on extracting paddy features through off-line image. The methodology involves image acquisition, converting the RGB images into a binary image using automatic thresholding based on local entropy threshold and Otsu method. A morphological algorithm is used to remove noises by using region filling technique. Then, the image characteristics consisting of lesion type, boundary colour, spot colour, and broken paddy leaf colour are extracted from paddy leaf images. Consequently, by employing production rule technique, the paddy diseases are recognized about 94.7 percent of accuracy rates. This prototype has a very great potential to be further improved in the future.

Automatic Detection and Quantification of WBCs and RBCs Using Iterative Structured Circle Detection Algorithm

Segmentation and counting of blood cells are considered as an important step that helps to extract features to diagnose some specific diseases like malaria or leukemia. The manual counting of white blood cells (WBCs) and red blood cells (RBCs) in microscopic images is an extremely tedious, time consuming, and inaccurate process. Automatic analysis will allow hematologist experts to perform faster and more accurately. The proposed method uses an iterative structured circle detection algorithm for the segmentation and counting of WBCs and RBCs. The separation of WBCs from RBCs was achieved by thresholding, and specific preprocessing steps were developed for each cell type. Counting was performed for each image using the proposed method based on modified circle detection, which automatically counted the cells. Several modifications were made to the basic (RCD) algorithm to solve the initialization problem, detecting irregular circles (cells), selecting the optimal circle from the candidate circles, determining the number of iterations in a fully dynamic way to enhance algorithm detection, and running time. The validation method used to determine segmentation accuracy was a quantitative analysis that included Precision, Recall, and F-measurement tests. The average accuracy of the proposed method was 95.3% for RBCs and 98.4% for WBCs.

Comparison of Feature Extractors in License Plate Recognition

Vehicle license plate recognition has been intensively studied in many countries. Due to the different types of license plates being used, the requirement of an automatic license plate recognition system is different for each country. In this paper, an automatic license plate recognition system is proposed for Malaysian vehicles with standard license plates using blob labeling and clustering for segmentation, seven popular and one proposed edge detectors for feature extraction and neural networks for classification. There were eight experiments conducted using eight different edge detectors: Kirsch, Sobel, Laplacian, Wallis, Prewitt, Frei Chen and a proposed edge detector. The result had shown kirsch edge detectors is the best technique for feature exractor while the proposed achieved better results compared to Prewitt, Frei Chen and Wallis

A novel statistical feature extraction method for textual images: Optical font recognition

The binary image is essential to image formats where the textual image is the best example of the binary image representation. Feature extraction is a fundamental process in pattern recognition. In this regard, pattern recognition studies involve document analysis techniques. Optical font recognition is among the pattern recognition techniques that are becoming popular today. In this paper, we propose an enhanced global feature extraction method based on the on statistical analysis of the behavior of edge pixels in binary images. A novel method in feature extraction for binary images has been proposed whereby the behavior of the edge pixels between a white background and a black pattern in a binary image captures information about the properties of the pattern. The proposed method is tested on an Arabic calligraphic script image for an optical font recognition application. To evaluate the performance of our proposed method, we compared it with a gray-level co occurrence matrix (GLCM). We classified the features using a multilayer artificial immune system, a Bayesian network, decision table rules, a decision tree, and a multilayer network to identify which approach is most suitable for our proposed method. The results of the experiments show that the proposed method with a decision tree classifier can boost the overall performance of optical font recognition.

A fast scheme for multilevel thresholding based on a modified bees algorithm

Image segmentation is one of the most important tasks in image processing and pattern recognition. One of the most efficient and popular techniques for image segmentation is image thresholding. Among several thresholding methods, Kapurs (maximum entropy (ME)) and Otsus methods have been widely adopted for their simplicity and effectiveness. Although efficient in the case of bi-level thresholding, they are very computationally expensive when extended to multilevel thresholding because they employ an exhaustive search for the optimal thresholds. In this paper, a fast scheme based on a modified Bees Algorithm (BA) called the Patch-Levy-based Bees Algorithm (PLBA) is adopted to render Kapurs (ME) and Otsus methods more practical; this is achieved by accelerating the search for the optimal thresholds in multilevel thresholding. The experimental results demonstrate that the proposed PLBA-based thresholding algorithms are able to converge to the optimal multiple thresholds much faster than their corresponding methods based on Basic BA. The experiments also show that the thresholding algorithms based on BA algorithms outperform corresponding state-of-the-art metaheuristic-based methods that employ Bacterial Foraging Optimization (BFO) and quantum mechanism (quantum-inspired algorithms) and perform better than the non-metaheuristic-based Two-Stage Multi-threshold Otsu method (TSMO) in terms of the segmented image quality. In addition, the results show the high degree of stability of the proposed PLBA-based algorithms.

A statistical global feature extraction method for optical font recognition

The study of optical font recognition has becoming more popular nowadays. In line to that, global analysis approach is extensively used to identify various font type to classify writer identity. Objective of this paper is to propose an enhanced global analysis method. Based on statistical analysis of edge pixels relationships, a novel method in feature extraction for binary images has proposed. We test the proposed method on Arabic calligraphy script image for optical font recognition application. We classify those images using Multilayer Network, Bayes network and Decision Tree classifiers to identify the Arabic calligraphy type. The experiments results shows that our proposed method has boost up the overall performance of the optical font recognition.

Patch-Levy-based initialization algorithm for Bees Algorithm

The Bees Algorithm (BA) is a population-based metaheuristic algorithm inspired by the foraging behavior of honeybees. This algorithm has been successfully used as an optimization tool in combinatorial and functional optimization fields. In addition, its behavior very closely mimics the actual behavior that occurs in nature, and it is very simple and easy to implement. However, its convergence speed to the optimal solution still needs further improvement and it also needs a mechanism to obviate getting trapped in local optima. In this paper, a novel initialization algorithm based on the patch concept and Levy flight distribution is proposed to initialize the population of bees in BA. Consequently, we incorporate this initialization procedure into a proposed enhanced BA variant. The proposed variant is more natural than conventional variants of BA. It mimics the patch environment in nature and Levy flight, which is believed to characterize the foraging patterns of bees in nature. The results of experiments conducted on several widely used high-dimensional benchmarks indicate that our proposed enhanced BA variant significantly outperforms other BA variants and state-of-the-art variants of the Artificial Bee Colony (ABC) algorithm in terms of solution quality, convergence speed, and success rate. In addition, the results of experimental analyses conducted indicate that our proposed enhanced BA is very stable, has the ability to deal with differences in search ranges, and rapidly converges without getting stuck in local optima.

Texture analysis for diagnosing paddy disease

The objective of this research is to develop a diagnosis system to recognize the paddy diseases, which are Blast Disease (BD), Brown-Spot Disease (BSD), and Narrow Brown-Spot Disease (NBSD). This paper concentrates on extracting paddy features through off-line image. The methodology involves converting the RGB images into a binary image using variable, global and automatic threshold based on Otsu method. A morphological algorithm is used to remove noises by using region filling technique. Then image characteristics consisting of lesion percentage, lesion type, boundary color, spot color, and broken paddy leaf color are extracted from paddy leaf images. Consequently, by employing production rule technique, the paddy diseases are recognized about 87.5 percent of accuracy rates. This prototype has a very great potential to be further improved in the future.

Character recognition based on global feature extraction

This paper presents a enhanced feature extraction method which is a combination and selected of two feature extraction techniques of Gray Level Co occurrence Matrix (GLCM) and Edge Direction Matrixes (EDMS) for character recognition purpose. It is apparent that one of the most important steps in a character recognition system is selecting a better feature extraction technique, while the variety of method makes difficulty for finding the best techniques for character recognition. The dataset of images that has been applied to the different feature extraction techniques includes the binary character with different sizes. Experimental results show the better performance of proposed method in compared with GLCM and EDMS method after performing the feature selection with neural network, bayes network and decision tree classifiers