Marcos Aurélio Batista

Image feature descriptor based on shape salience points

Abstract The work presented in this article aims at shape feature extraction and description. In this paper, we propose a shape-based image retrieval technique using salience points to describe shapes. The saliences of a shape are defined as the higher curvature points along the shape contour. The technique presented here consists of: a salience point detector; a salience representation using angular relative position and curvature value analyzed from a multi-scale perspective; and a matching algorithm considering local and global features to calculate the dissimilarity. The proposed technique is robust to noise and presents good performance when dealing with shapes of different classes but visually similar. The experiments were made in order to illustrate the performance of the proposed technique, and the results show the good performance of our method when compared with other shape-based methods in literature.

Adaptive Image Retrieval through the Use of a Genetic Algorithm

In this work an image retrieval system adaptable to users interests by the use of relevance feedback via genetic algorithm is presented. The retrieval process is based on local similarity patterns. The goal of the genetic algorithm is to infer weights for regions and features that better translate the users requirements producing better quality rankings. The genetic algorithm used has as its main innovation an order-based fitness function, which is appropriate to the ranking requirements of a majority of the users. This fitness function will quickly drive the genetic algorithm in the process of searching for an optimal solution. Evaluations in several databases have shown the robustness and efficiency of the proposed retrieval method even when the query is a sketch or damaged image.Logic and proofs constitute key factors in increasing the user trust towards the semantic Web. Defeasible reasoning is a useful tool towards the development of the logic layer of the semantic Web architecture. However, having a solid mathematical notation, it may be confusing to end users, who often need graphical trace and explanation mechanisms for the derived conclusions. In a previous work of ours, we outlined a methodology for representing defeasible logic rules, utilizing directed graphs that feature distinct node and connection types. However, visualizing a defeasible logic rule base also involves the placement of the multiple graph elements in an intuitive way, a non-trivial task that aims at improving user comprehensibility. This paper presents a stratification algorithm for visualizing defeasible logic rule bases that query and reason about RDF data as well as a tool that applies this algorithm.

Image restoration using digital inpainting and noise removal

Inpainting and denoising are two important tasks in the field of image processing with broad applications in image and vision analysis. In this paper, we present a new approach for image restoration. Our method simultaneously fills in missing, corrupted, or undesirable information while it removes noise. The denoising is performed by the smoothing equation working inside and outside of the inpainting domain but in completely different ways. Inside the inpainting domain, the smoothing is carried out by the Mean Curvature Flow, while the smoothing of the outside of the inpainting domain is carried out in a way as to encourage smoothing within a region and discourage smoothing across boundaries. Besides smoothing, the approach here presented permits the transportation of available information from the outside towards the inside of the inpainting domain. This combination permits the simultaneous use of filling-in and differentiated smoothing of different regions of an image. The experimental results show the effective performance of the combination of these two procedures in restoring scratched photos, disocclusion (or removal of entire objects from the image) in vision analysis and text removal from images.

Image inpainting and denoising by nonlinear partial differential equations

A new approach is presented for recovering shapes from noisy and damaged images as well as the filling in of missing information or the removal of objects from an image. The procedure allows for the denoising and inpainting of images simultaneously. The denoising is performed by the smoothing equation working inside and outside of the inpainting domain but in completely different ways. Inside the inpainting domain the smoothing is carried out by the mean curvature flow, while the smoothing of the outside of the inpainting domain is carried out in a way to encourage smoothing within a region and discourage smoothing across boundaries. Besides smoothing, the approach here presented permits the transportation of available information from the outside towards the inside of the inpainting domain. This combination permits the simultaneous use of filling-in and differentiated smoothing of different regions of an image. The experimental results show the effective performance of the combination of these two procedures in image restoration.

An image retrieval system using shape salience points

Content-Based Image Retrieval (CBIR) systems have been developed to support the image retrieval based on image properties, such as color, shape and texture. In this paper, we are concerned with shape-based image retrieval. In this context, we propose a method to describe shapes based on salience points. The proposed descriptor utilizes a salience detector which is robust to noise, and an elastic matching algorithm to measure the similarity between two shapes represented by their salience points. The proposed approach is robust to noise and gives good results in recognizing shapes of the same class, even if they are represented by a different number of salience points.

A shape contour descriptor based on salience points

In this paper, we propose a shape-based image retrieval technique using salience points to describe shapes. This technique consists of a salience point detector robust to noise, a salience representation using angular relative position and curvature value, invariant to rotation, translation and scaling, and an elastic matching algorithm to analyze the similarity. The proposed technique is robust to noise and presents good performance when dealing with shapes of different class but visually similar. The experiments were made in order to illustrate the performance of the proposed technique. The results show the good performance of our method when comparing with other shape-based methods in the literature.

Suspicious event recognition using infrared imagery

The societys concern about safety is growing every day and with it the demand for intelligent surveillance systems with the minimal human intervention possible. In this work we identify suspicious events that could take place in a parking lot based on infrared imagery. The object segmentation process is performed using a dynamic background-subtraction technique which robustly adapts detection to illumination changes. Segmented objects are tracked by a two phase function: prediction and correction. During the tracking process the objects are classified into two categories: Person and Vehicles, based on features like size, velocity and temperature. With the objects correctly segmented and classified using features like velocity and time stood in one spot, it is possible to identify suspicious events occurring in the monitored area. Experimental results are presented to demonstrate the effectiveness of the proposed technique to recognize suspicious events.

Image Characterization via Multilayer Neural Networks

The achievement of image retrieval systems severally depends on the way the data is represented. This paper proposes a new image representation through an intelligent mechanism via neural networks for semantic-gap and dimensionality reduction. The goal of the multilayer neural network is to represent high-level semantic concepts and knowledge through a pre-defined set of images. As a consequence of this low-level into high-level feature transformation there is a semantic gap reduction between human perception and automatic feature extraction. The experimental results show the effective performance of the proposed technique.

Geodesic path based digital inpainting

Abstract The filling-in technique has been used since the Renascence period and its main goal is to reconstruct missing parts or damaged areas in an image in such a way as to restore its harmony. In artwork restoration, this process is called inpainting. After the original work of Bertalmio, Sapiro, Caselles and Ballester several different approaches have been used to tackle the digital inpainting problem. Some are based on Partial Differential Equations to model a transportation process and a diffusion process, others are based on the Euler elastica functional. This paper presents a model for completing missing parts using the geodesic path continuation to perform the filling-in of the inpainting domain D . The model is proposed in a way as to satisfy the “ Connectivity Principle ”. The image u ( x , y ) is represented by a family of level lines and the missing part of the image is filled-in by the propagation of the available surrounding information, from outside to inside of the inpainting domain D along the geodesic paths of the image. After defining the domain D the restoration process becomes automatic and the final result u ( x , y , t n ) is carried out by the evolutionary process starting with the initial degraded image u ( x , y , 0 ) . In the proposed model, no limitations are imposed on the topology of the domain D , even permitting holes within the domain. Examples on real and textured images show the performance of this proposed model.

An image retrieval system adaptable to user's interests by the use of relevance feedback via genetic algorithm

The emergence of multimedia technology and the rapid expansion of image sets on the internet have attracted a lot of research tools for effective retrieval of visual data. When working in the image retrieval context the main goal is to retrieve images which might be useful or relevant to the user based on features automatically extracted from the images. The proposal of this work is to integrate the information provided by the user into the decision procedure by the use of the relevance feedback mechanism. The relevance feedback technique used is based on genetic algorithms using a proposed order-based fitness function in order to adapt the users image similarity criteria. Image similarity is expressed as a weighted integration of color, shape and texture features. The retrieval process itself is based on the Local Similarity Pattern, where the image areas are uniformly partitioned into regions, and the similarity between the images is measured by corresponding region similarities. The use of negative and positive weights for the features, into the genetic algorithm, allows one to express, in a continuous way, the concepts of relevance, irrelevance and undesirability in the similarity model used. Experiments in a database with 12750 images has shown that the integration of features through the proposed genetic algorithm into a relevance feedback mechanism provides good results in the image retrieval context.