No abstract

Convolutional Neural Network is an important deep learning architecture for computer vision. Alongside with its variations, it brought image analysis applications to a new performance level. However, despite its undoubted quality, the evaluation of the performance presented in the literature is mostly restricted to accuracy measurements. So, considering the stochastic characteristics of neural networks training and the impact of the architectures configuration, research is still needed to affirm if such architectures reached the optimal configuration for their focused problems. Statistical significance is a powerful tool for a more accurate experimental evaluation of stochastic processes. This paper is dedicated to perform a thorough evaluation of kernel order influence over convolutional neural networks in the context of traffic signs recognition. Experiments for distinct kernels sizes were performed using the most well accepted database, the socalled German Traffic Sign Recognition Benchmark.

This paper describes a technique for an automatic polar map creation from myocardial perfusion SPECT images. This exam is widely used in post-infarction patient evaluations, in order to foretell the outcome and left ventricular function. This exam is difficult to interpret, since it is a 3D representation of the heart. Use of polar maps intends to simplify analysis of the exam, converting the 3D image into a 2D plot. The technique developed is based on a combination of image registration and feature detection. For this study, an overall of 31 cases were tested, with the results compared with the gold standard software. The correlation calculated between techniques was 0.76 in the worst case and 0.98 in the best case. Index Terms: Image Registration, Myocardial Infarction, Polar Map, SPECT.

No abstract

No abstract