DarwinGSE: Towards better image retrieval systems for intellectual property datasets.

A trademark's image is usually the first type of indirect contact between a consumer and a product or a service. Companies rely on graphical trademarks as a symbol of quality and instant recognition, seeking to protect them from copyright infringements. A popular defense mechanism is graphical searching, where an image is compared to a large database to find potential conflicts with similar trademarks. Despite not being a new subject, image retrieval state-of-the-art lacks reliable solutions in the Industrial Property (IP) sector, where datasets are practically unrestricted in content, with abstract images for which modeling human perception is a challenging task. Existing Content-based Image Retrieval (CBIR) systems still present several problems, particularly in terms of efficiency and reliability. In this paper, we propose a new CBIR system that overcomes these major limitations. It follows a modular methodology, composed of a set of individual components tasked with the retrieval, maintenance and gradual optimization of trademark image searching, working on large-scale, unlabeled datasets. Its generalization capacity is achieved using multiple feature descriptions, weighted separately, and combined to represent a single similarity score. Images are evaluated for general features, edge maps, and regions of interest, using a method based on Watershedding K-Means segments. We propose an image recovery process that relies on a new similarity measure between all feature descriptions. New trademark images are added every day to ensure up-to-date results. The proposed system showcases a timely retrieval speed, with 95% of searches having a 10 second presentation speed and a mean average precision of 93.7%, supporting its applicability to real-word IP protection scenarios.

Developments in Image Processing Using Deep Learning and Reinforcement Learning.

The growth in the volume of data generated, consumed, and stored, which is estimated to exceed 180 zettabytes in 2025, represents a major challenge both for organizations and for society in general. In addition to being larger, datasets are increasingly complex, bringing new theoretical and computational challenges. Alongside this evolution, data science tools have exploded in popularity over the past two decades due to their myriad of applications when dealing with complex data, their high accuracy, flexible customization, and excellent adaptability. When it comes to images, data analysis presents additional challenges because as the quality of an image increases, which is desirable, so does the volume of data to be processed. Although classic machine learning (ML) techniques are still widely used in different research fields and industries, there has been great interest from the scientific community in the development of new artificial intelligence (AI) techniques. The resurgence of neural networks has boosted remarkable advances in areas such as the understanding and processing of images. In this study, we conducted a comprehensive survey regarding advances in AI design and the optimization solutions proposed to deal with image processing challenges. Despite the good results that have been achieved, there are still many challenges to face in this field of study. In this work, we discuss the main and more recent improvements, applications, and developments when targeting image processing applications, and we propose future research directions in this field of constant and fast evolution.

A Novel Trademark Image Retrieval System Based on Multi-Feature Extraction and Deep Networks.

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.

Graphical Image Region Extraction with K-Means Clustering and Watershed.

With a wide range of applications, image segmentation is a complex and difficult preprocessing step that plays an important role in automatic visual systems, which accuracy impacts, not only on segmentation results, but directly affects the effectiveness of the follow-up tasks. Despite the many advances achieved in the last decades, image segmentation remains a challenging problem, particularly, the segmenting of color images due to the diverse inhomogeneities of color, textures and shapes present in the descriptive features of the images. In trademark graphic images segmentation, beyond these difficulties, we must also take into account the high noise and low resolution, which are often present. Trademark graphic images can also be very heterogeneous with regard to the elements that make them up, which can be overlapping and with varying lighting conditions. Due to the immense variation encountered in corporate logos and trademark graphic images, it is often difficult to select a single method for extracting relevant image regions in a way that produces satisfactory results. Many of the hybrid approaches that integrate the Watershed and K-Means algorithms involve processing very high quality and visually similar images, such as medical images, meaning that either approach can be tweaked to work on images that follow a certain pattern. Trademark images are totally different from each other and are usually fully colored. Our system solves this difficulty given it is a generalized implementation designed to work in most scenarios, through the use of customizable parameters and completely unbiased for an image type. In this paper, we propose a hybrid approach to Image Region Extraction that focuses on automated region proposal and segmentation techniques. In particular, we analyze popular techniques such as K-Means Clustering and Watershedding and their effectiveness when deployed in a hybrid environment to be applied to a highly variable dataset. The proposed system consists of a multi-stage algorithm that takes as input an RGB image and produces multiple outputs, corresponding to the extracted regions. After preprocessing steps, a K-Means function with random initial centroids and a user-defined value for k is executed over the RGB image, generating a gray-scale segmented image, to which a threshold method is applied to generate a binary mask, containing the necessary information to generate a distance map. Then, the Watershed function is performed over the distance map, using the markers defined by the Connected Component Analysis function that labels regions on 8-way pixel connectivity, ensuring that all regions are correctly found. Finally, individual objects are labelled for extraction through a contour method, based on border following. The achieved results show adequate region extraction capabilities when processing graphical images from different datasets, where the system correctly distinguishes the most relevant visual elements of images with minimal tweaking.

Segmentation of fetal ultrasound images.

This paper describes a new method for segmentation of fetal anatomic structures from echographic images. More specifically, we estimate and measure the contours of the femur and of cranial cross-sections of fetal bodies, which can thus be automatically measured. Contour estimation is formulated as a statistical estimation problem, where both the contour and the observation model parameters are unknown. The observation model (or likelihood function) relates, in probabilistic terms, the observed image with the underlying contour. This likelihood function is derived from a region-based statistical image model. The contour and the observation model parameters are estimated according to the maximum likelihood (ML) criterion, via deterministic iterative algorithms. Experiments reported in the paper, using synthetic and real images, testify for the adequacy and good performance of the proposed approach.