Mohamed Nabil Saidi

Automatic target recognition of aircraft models based on ISAR images

In this paper, we present a system for aircraft automatic target recognition (ATR) using Inverse Synthetic Aperture Radar (ISAR) and based on Knowledge discovery from data process adapted to radar domain. We propose a method for target shape extraction from ISAR images based on the combination of two methods, SUSAN modified and active deformable contours via level set. In the second part of this work, we propose to fuse two commonly used shape descriptors algorithms based on moments Invariant and Fourier descriptors. We have investigated the impact of the information fusion on the recognition rate. The classification scheme is ensured using support vector machine (SVM) classifier. Several combination strategies are compared at score/decision/feature level. Experimental results of the proposed method are provided and discussed.

Automatic recognition of ISAR Images: Target shapes features extraction

This paper presents a part of research study dealing with the initialization of an information system on radar automatic target recognition (ATR) chain. In this framework, we propose a set of helpful information at different levels of the ATR chain for decision making. The methodology used is the knowledge discovery process from data (KDD process).we focused in this paper on the data preparation step, more precisely Speckle denoising, edge detection and computation of features vector. We present the results of a several speckle filters that are largely used by ISAR imaging scientists (Lee, Frost, Kuan...). Fourier Descriptors have been used as features of the objects. Various similarity measures have been used and compared for target recognition.

Score fusion in multibiometric identification based on fuzzy set theory

Multimodal biometric systems consolidate or fuse information from multiple biometric sources. They have been developed to overcome several limitations of each individual biometric system, such as sensitivity to noise, intra class invariability, data quality, non-universality and other factors. In this paper, we propose a general framework of multibiometric identification system based on fusion at matching score level using fuzzy set theory. The motivation for using fuzzy set theory is that it offers methods suited to treat (modeling, fusion,...) and take into account the information inherently uncertain and ambiguous. We note that our fusion system is based on face and iris modalities. Experimental results exhibit that the proposed method performance bring obvious improvement compared to unimodal biometric identification methods and classical combination approaches at score level fusion.

Fuzzy pattern recognition-based approach to biometric score fusion problem

Abstract This paper introduces a novel approach for biometric score fusion problem that can be viewed as a fuzzy pattern recognition one. In this approach, the matching score space is considered as consisting of two fuzzy sets (“genuine” and “impostor”). First, each individual matcher is modeled as a fuzzy set, using an automatic membership function generation method, in order to handle uncertainty and imperfection in matching scores. Then, the new fuzzy matching scores are fused with a fuzzy aggregation operator, and the final decision is given. Experimental results on well-known benchmark databases show that our method significantly improves single best biometric matcher performance, and reaches comparable results to several relevant methods. Moreover, the proposed method exhibits high robustness to small size of client training data.

A CAD System for the Detection of Abnormalities in the Mammograms Using the Metaheuristic Algorithm Particle Swarm Optimization (PSO)

The discovery of a malignant mass in the breast is considered one of the most devastating and depressing health issue women can face. However an early detection can be so helpful and could bring hope to control the disease and even cure it. Nowadays In spite the fact that Digital mammograms have proven to be an efficient tool for the screening of breast cancer, an accurate detection of the abnormalities remains a challenging task for radiologists. In this paper, we propose an effective method for the detection and classification of the suspicious regions. In our proposed approach, we use Entropy thresholding for pectoral muscle removal, and we extract the region of interest (ROI) using the Metaheuristic algorithm Particle Swarm Optimization (PSO). Then we extract Shape and texture features from the abnormalities using Fourier transform and Gray Level Co-Occurrence Matrix (GLCM) respectively. The classification of the detected abnormalities is carried out through the Support Vector Machine, which classifies the segmented region into normal and abnormal based on the extracted features.

Pose estimation for ISAR image classification

This paper presents aircraft target recognition (ATR) system using Inverse Synthetic Aperture Radar (ISAR) images. Knowing the pose of the target can improve the ATR performance (recognition rate and computational complexity). So, we propose in this paper a new pose estimator from ISAR images, based on the axis of symmetry and the similarity measure. The method proposed is compared with several approaches proposed recently in the literature, such as 2-D Continuous wavelet Transform and Hough transform. Once the pose of target is estimated, the classification if finally performed by K-Nearest Angle (KNA) classifier which insert the pose information into image retrieval task.

Applying the Upper Integral to the Biometric Score Fusion Problem in the Identification Model

This paper presents a new biometric score fusion approach in an identification system using the upper integral with respect to Sugeno’s fuzzy measure. First, the proposed method considers each individual matcher as a fuzzy set in order to handle uncertainty and imperfection in matching scores. Then, the corresponding fuzzy entropy estimates the reliability of the information provided by each biometric matcher. Next, the fuzzy densities are generated based on rank information and training accuracy. Finally, the results are aggregated using the upper fuzzy integral. Experimental results compared with other fusion methods demonstrate the good performance of the proposed approach.

Multispectrals images segmentation based on DWT and decisions fusion

This paper aims to present a supervised segmentation algorithm based on data fusion for the textured image. The feature extraction method that is used for segmentation is Discrete Wavelet Transform (DWT). In the stage of segmentation, the estimated feature vector of each pixel is sent to Support Vector Machine classifier for an initial labelling. To obtain a more accurate result of segmentation, we integrated a high-level data fusion by combining decisions made by the same classifier. Finally, the performance of the proposed segmentation algorithm is demonstrated on a variety of images.

Detection of breast abnormalities in digital mammograms using the electromagnetism-like algorithm

The detection of abnormalities in the breast at an early stage can be so helpful for breast cancer treatment. Currently, mammography is the cheapest and the most efficient technique in terms of identifying the suspicious lesions in the breast. However, the interpretation of this screening remains so hard and could lead to inaccurate detection known as false positive and false negative. Dense breast mammograms particularly are difficult to read because they may contain abnormal structures that are similar to the normal breast tissue. In this paper, we introduce an effective method for the detection of the ambiguous areas in digital mammograms. After noise and artifacts removal from the images using 2D Median filtering and labeling, we isolate the abnormalities using the meta-heuristic algorithm Electromagnetism-like Optimization (EML). The segmentation was carried on the abnormal cases of two different databases Mini-Mias and DDSM. The accuracy detection rate achieves almost 85% for both databases and 91.07% for DDSM alone.

Texture Segmentation Based on Dual Tree Complex Wavelet Transform and Support Vector Machine

This paper presents a new approach for segmentation of the textured images that exploits properties of the dual-tree complex wavelet transform, shift invariance and six directional sub-bands at each scale, and uses a feature vector comprising of mean and standard deviation of the six directional sub-bands over a sliding window. The classification of each sliding window using Support Vector Machine (SVM) leads to a segmented image. Through experiments on a variety of synthetic images of texture data sets, we show that our algorithm yields significant performance improvements for texture segmentation, as compared with other state-of-the-art methods of feature extraction.