Graphical Search Engines are conceptually used in many development areas surrounding information retrieval systems that aim to provide a visual representation of results, typically associated with retrieving images relevant to one or more input images. Since the 1990s, efforts have been made to improve the result quality, be it through improved processing speeds or more efficient graphical processing techniques that generate accurate representations of images for comparison. While many systems achieve timely results by combining high-level features, they still struggle when dealing with large datasets and abstract images. Image datasets regarding industrial property are an example of an hurdle for typical image retrieval systems where the dimensions and characteristics of images make adequate comparison a difficult task. In this paper, we introduce an image retrieval system based on a multi-phase implementation of different deep learning and image processing techniques, designed to deliver highly accurate results regardless of dataset complexity and size. The proposed approach uses image signatures to provide a near exact representation of an image, with abstraction levels that allow the comparison with other signatures as a means to achieve a fully capable image comparison process. To overcome performance disadvantages related to multiple image searches due to the high complexity of image signatures, the proposed system incorporates a parallel processing block responsible for dealing with multi-image search scenarios. The system achieves the image retrieval through the use of a new similarity compound formula that accounts for all components of an image signature. The results shows that the developed approach performs image retrieval with high accuracy, showing that combining multiple image assets allows for more accurate comparisons across a broad spectrum of image typologies. The use of deep convolutional networks for feature extraction as a means of semantically describing more commonly encountered objects allows for the system to perform research with a degree of abstraction.

Data science techniques have increased in popularity over the last decades due to its numerous applications when handling complex data, but also due to its high precision. In particular, Machine (ML) and Deep Learning (DL) systems have been explored in many unique applications, owing to their high precision, flexible customization, and strong adaptability. Our research focuses on a previously described image detection system and analyses the application of a user feedback system to improve the accuracy of the comparison formula. Due to the non-traditional requirements of our system, we intended to assess the performance of multiple AI techniques and find the most suitable model to analyze our data and implement possible improvements. The study focuses on a set of test data, using the test results collected for one particular image cluster. We researched some of the previous solutions on similar topics and compared multiple ML methods to find the most suitable model for our results. Artificial Neural networks and binary decision trees were among the better performing models tested. Reinforcement and Deep Learning methods could be the focus of future studies, once more varied data are collected, with bigger comparison weight diversity.