Evandro Luis Linhari Rodrigues

Methodology for classification of images based on the characteristics of a new interpretation of Shannon’s entropy

A new visual inspection method for the classification of wooden plates used in pencil manufacturing is presented. Darker regions in wooden plates indicate the presence of growth rings which are regions of hard wood. Pencils manufactured with these plates are more difficult to sharpen and have a tendency to bend and crack; therefore, these plates are classified as not being adequate for pencil manufacturing. The proposed method is based on the extraction and analysis of the features of the wooden plates using gray level images. The method classifies the plates using the results obtained by an automatic threshold determination based on Shannon’s entropy. The method was idealized aiming at low computational complexity, i.e., algorithm calculations involving only simple operations such as addition, subtraction, multiplication and division which could be implemented in hardware using VLSI technology or programmable logic devices. The wooden plate is mapped in an optimal number of regions; each region is pre-classified considering some relevant features based on the entropy gray level distribution of the pixels. Information from all regions is combined based on heuristic decision rules, arriving in a pre-classification stage where the regions are labeled in four classes (A, B, C and X). Two decision algorithms have been investigated for the final classification: one based in a co-occurrence matrix considering only a uni-directional horizontal neighborhood of the regions and the second is based on a heuristic method of information reduction considering combinations of the pre-classified regions. The final results obtained by the two algorithms were compared with the classification made by a human expert, demonstrating that the proposed method had very good performance.

Maturidade óssea: estimação por simplificações do método de Eklof e Ringertz

OBJECTIVE: The present study was aimed at presenting a process for estimating bone age by means of automatic simplifications of the Eklof & Ringertz method to provide reports as an aid to clinical diagnosis. MATERIALS AND METHODS: Carpal images from children and teenagers in the age range between 6 and 16 years were utilized for estimating their bone age based on simplifications ER5 and ER3, analyzing respectively 5 and 3 ossification centers. The automation of simplified methods utilizes specific procedures for processing radiographic images of the hand. RESULTS: The authors observed a high agreement with the average of medical reports based on the three classical methods (Greulich & Pyle, Tanner & Whitehouse, Eklof & Ringertz). The analysis of agreement with the proposed simplifications was performed with the paired Student’s t-test considering a significance level of 5% and, in most of cases, statistically significant differences were not observed (p < 0.05). CONCLUSION: Based on the present results, it is concluded that simplifications of the Eklof & Ringertz method allow a reliable, fast and automated estimation of the bone age. Additionally, the proposed simplifications are appropriate for estimating bone age on extensive data bases without the subjectivity that is present in the classical methods.

A Reference Model as Automated Process for Software Adaptation at Runtime

The development of self-adaptive software (SaS) has specific characteristics compared to traditional one, since it allows that changes to be incorporated at runtime. Automated processes have been used as a feasible solution to conduct the software adaptation at runtime. In parallel, reference model has been used to aggregate knowledge and architectural artifacts, since capture the systems essence of specific domains. However, there is currently no reference model based on reflection for the development of SaS. Thus, the main contribution of this paper is to present a reference model based on reflection for development of SaS that have a need to adapt at runtime. To present the applicability of this model, a case study was conducted and good perspective to efficiently contribute to the area of SaS has been obtained.

True-Motion Estimation and Compensation with Multitemporal Block-Matching Search

in de-interlacing algorithms are fundamental to explore image quality potential on modern TV screen technologies. This paper presents a true motion vector verification algorithm based on multi temporal block matching strategy, applied to video de-interlacing. During field scanning, a block of pixels is selected, then a block with the same reference coordinates is extracted but in the future field. A searching process runs in the previous field, looking for the most similar block; the best fit block and their coordinates are extracted from the previous field, and a new searching process is done but in the future field. If the searching process in the future field results back to the original block coordinates, the motion vector is validated; in other case, a correction over the motion vectors is done. Error calculation showed that the proposed algorithm presents image quality improvement, when compared to a classical motion compensation algorithm.

High-boost Weber local filter for precise eye localization under uncontrolled scenarios

Abstract The task of precise eye localization for a given face is very important for many computer vision applications such as face recognition, face and eye tracking, and face alignment. Further, this is a challenging task when performed in uncontrolled scenarios. This paper proposes a new method for precise eye localization in uncontrolled scenarios using the high-boost Weber local filter (HBWLF); the proposed filter emphasizes high-frequency components, without eliminating the low-frequency ones, and thus enhances the details of the periocular region (region around the eyes), which is critical to the task of eye localization. The proposed method was evaluated using Labeled Faces in the Wild (LFW) and BioID databases, and the results show that HBWLF yields better performance than several classical methods.

Analysis of polynomial behavior of the C3 cervical concavity to bone age estimation using artificial neural networks

The bone age estimation is obtained by radiographic analysis of any bone in human body, which is considered as important information for medical and orthodontic diagnosis. The use of lateral cephalograms for bone age reports reduces the patients exposure to ionizing radiation because this radiography is usually requested for orthodontic treatments. This paper presents a novel methodology for mapping the behavior of C3 vertebra concavity (presented in lateral cephalograms) related to bone age. A 4th degree polynomial is used to describe the concavity. Its coefficients are the input of an artificial neural network. Thus, the best topology is chosen based on the correlation coefficient between the output of the network and bone age. After obtaining and analyzing several metrics, the results related to neural network application are expressive, achieving near 0.9 of correlation and the results related to bone age estimation are promising, with mean absolute error around 0.8 years. The results allow the conclusion that just one feature (C3 concavity) has high correlation with bone age.

Embedded System Design: An Overview of Brazilian Development

Brazil, like other emerging countries such as China and India are increasing significantly their importance as global players. The Brazilian economic relevance gains more importance with its economic growth and industry expansion. This economic growth also reflects on embedded systems design that expands following the market demand for new products. The Brazilian developments are ubiquitous in different areas: industrial automation, automobiles, home appliances, electronic consumers etc. A statistical survey was conducted to evaluate the embedded system development in Brazil, to identify the developers profile and the main characteristics of embedded projects. The main results indicate that Brazilian embedded developer is generally young, no older than 35 years old and has a maximum of 10 years of embedded system design experience. They also show that embedded project developed in Brazil, are commonly linked to new products, last more than 6 months and usually are delayed considering the initial schedule.