Evaluation of Distance Measures for Feature based Image Registration using AlexNet

Abstract

Image registration is a classic problem of computer vision with several applications across areas like defence, remote sensing, medicine etc. Feature based image registration methods traditionally used hand-crafted feature extraction algorithms, which detect key points in an image and describe them using a region around the point. Such features are matched using a threshold either on distances or ratio of distances computed between the feature descriptors. Evolution of deep learning, in particular convolution neural networks, has enabled researchers to address several problems of vision such as recognition, tracking, localization etc. Outputs of convolution layers or fully connected layers of CNN which has been trained for applications like visual recognition are proved to be effective when used as features in other applications such as retrieval. In this work, a deep CNN, AlexNet, is used in the place of handcrafted features for feature extraction in the first stage of image registration. However, there is a need to identify a suitable distance measure and a matching method for effective results. Several distance metrics have been evaluated in the framework of nearest neighbour and nearest neighbour ratio matching methods using benchmark dataset. Evaluation is done by comparing matching and registration performance using metrics computed from ground truth.

Система Ідентифікації Оригіналу Відео За Його Фрагментом З Використанням Згорткових Нейронних Мереж

“…Наступний модуль системи -це модуль пошуку, який відповідає за зіставлення ключових векторів вхідного фрагменту відео із тими, що вже знаходяться в базі. Процес, що містить визначення подібності [7], використовує такі основні концепції:…”

“…Вибір ефективної функції подібності векторів базується на дослідженні [7], де розглянуто низку популярних методів та порівняння метрик експериментальних застосувань. Причому вхідними векторами для порівняння є результат останнього незв'язного шару згорткової нейронної мережі, що є ідентичним способом і в запропонованій системі.…”

Product Re-identification System in Fully Automated Defect Detection

“…The Inria Holidays and Oxford Buildings datasets were used for their experiments, which revealed that the fusion feature could contribute to the improvement of image retrieval. Besides those works that we discussed above, there are many AlexNet's applications in extracting features for hand gestures, remote sensing images, image registration and bearing fault diagnosis as well [33], [34], [36]- [38].…”

Facial emotion recognition using deep convolutional neural network and smoothing, mixture filters applied during preprocessing stage

“…The action units [5], [6] of the face are the fundamental unit of the expression which contain sensitive information of expression. Convolutional neural network (CNN) consist of convolutional layer, pooling layer and fully connected network [7] is the most interesting tool and technology that, produces promising result [8] for any high-level scientific computation [9], [10]. Convolutional neural networks are not only for facial emotion recognition that we applied in the under described research, but also in several classifications such as human disease classification [11], [12], and plant disease classification [13].…”