Evangelos G. Karakasis

Novel moment invariants for improved classification performance in computer vision applications

A novel set of moment invariants based on the Krawtchouk moments are introduced in this paper. These moment invariants are computed over a finite number of image intensity slices, extracted by applying an innovative image representation scheme, the image slice representation (ISR) method. Based on this technique an image is decomposed to a several non-overlapped intensity slices, which can be considered as binary slices of certain intensity. This image representation gives the advantage to accelerate the computation of images moments since the image can be described in a number of homogenous rectangular blocks, which permits the simplification of the computation formulas. The moments computed over the extracted slices seem to be more efficient than the corresponding moments of the same order that describe the whole image, in recognizing the pattern under processing. The proposed moment invariants are exhaustively tested in several well known computer vision datasets, regarding their rotation, scaling and translation (RST) invariant recognition performance, by resulting to remarkable outcomes.

Moment-based local binary patterns: A novel descriptor for invariant pattern recognition applications

A novel descriptor able to improve the classification capabilities of a typical pattern recognition system is proposed in this paper. The introduced descriptor is derived by incorporating two efficient region descriptors, namely image moments and local binary patterns (LBP), commonly used in pattern recognition applications, in the last decades. The main idea behind this novel feature extraction methodology is the need of improved recognition capabilities, a goal achieved by the combinative use of these descriptors. This collaboration aims to make use of the major advantages each one presents, by simultaneously complementing each other, in order to elevate their weak points. In this way, the useful properties of the moments and moment invariants regarding their robustness to the noise presence, their global information coding mechanism and their invariant behaviour under scaling, translation and rotation conditions, along with the local nature of the LBP, are combined in a single concrete methodology. As a result a novel descriptor invariant to common geometric transformations of the described object, capable to encode its local characteristics, is formed and its classification capabilities are investigated through massive experimental scenarios. The experiments have shown the superiority of the introduced descriptor over the moment invariants, the LBP operator and other well-known from the literature descriptors such as HOG, HOG-LBP and LBP-HF.

A unified methodology for the efficient computation of discrete orthogonal image moments

A novel methodology is proposed in this paper to accelerate the computation of discrete orthogonal image moments. The computation scheme is mainly based on a new image representation method, the image slice representation (ISR) method, according to which an image can be expressed as the outcome of an appropriate combination of several non-overlapped intensity slices. This image representation decomposes an image into a number of binary slices of the same size whose pixels come in two intensities, black or any other gray-level value. Therefore the image block representation can be effectively applied to describe the image in a more compact way. Once the image is partitioned into intensity blocks, the computation of the image moments can be accelerated, as the moments can be computed by using decoupled computation forms. The proposed algorithm constitutes a unified methodology that can be applied to any discrete moment family in the same way and produces similar promising results, as has been concluded through a detailed experimental investigation.

Image moment invariants as local features for content based image retrieval using the Bag-of-Visual-Words model

A new image descriptor specifically designed for image retrieval tasks is introduced.Evaluation of affine moment invariants in the area of image retrieval.The usage of image chromaticities improves the overall retrieval performance. This paper presents an image retrieval framework that uses affine image moment invariants as descriptors of local image areas. Detailed feature vectors are generated by feeding the produced moments into a Bag-of-Visual-Words representation. Image moment invariants have been selected for their compact representation of image areas as well as due to their ability to remain unchanged under affine image transformations. Three different setups were examined in order to evaluate and discuss the overall approach. The retrieval results are promising compared with other widely used local descriptors, allowing the proposed framework to serve as a reference point for future image moment local descriptors applied to the general task of content based image retrieval.

A Unified Methodology for Computing Accurate Quaternion Color Moments and Moment Invariants

In this paper, a general framework for computing accurate quaternion color moments and their corresponding invariants is proposed. The proposed unified scheme arose by studying the characteristics of different orthogonal polynomials. These polynomials are used as kernels in order to form moments, the invariants of which can easily be derived. The resulted scheme permits the usage of any polynomial-like kernel in a unified and consistent way. The resulted moments and moment invariants demonstrate robustness to noisy conditions and high discriminative power. Additionally, in the case of continuous moments, accurate computations take place to avoid approximation errors. Based on this general methodology, the quaternion Tchebichef, Krawtchouk, Dual Hahn, Legendre, orthogonal Fourier-Mellin, pseudo Zernike and Zernike color moments, and their corresponding invariants are introduced. A selected paradigm presents the reconstruction capability of each moment family, whereas proper classification scenarios evaluate the performance of color moment invariants.

Adaptive color image watermarking by the use of quaternion image moments

Abstract The first adaptive moment-based color image watermarking is presented in this work. The proposed method exploits rotation invariance, high reconstruction capability and computation accuracy of the quaternion radial moments’ (QRMs), subject to the tradeoff between robustness and imperceptibility. The current system manages to multi-embed binary logos to color images applying QRMs as information carriers. A novel adaptive system adjusts the watermark’s embedding strength (online) by taking into account image’s morphology, with respect to robustness and imperceptibility. The method manages to experimentally justify and further eliminate the attack-free phenomenon that state-of-the-art methods suffer. The simulation results justified that the proposed framework manages to highly secure its carrying information under common signal processing and geometric attacking conditions. Furthermore, the adoption of the novel adaptive process enhances the robustness and imperceptibility requirements by reducing the Bit Error Rate even by 49% and producing even 5db higher PSNR values, respectively.

Computation strategies of orthogonal image moments: A comparative study

This paper discusses possible computation schemes that have been introduced in the past and cope with the efficient computation of the orthogonal image moments. An exhaustive comparative study of these alternatives is performed in order to investigate the conditions under which each scheme ensures high computation rates, for several test images. The present study aims to discover the properties and the behaviour of the different methodologies and it serves as a reference point in the field of moments computation. Some useful conclusions are drawn regarding the applicability and the usefulness of the computation strategies in comparison and efficient hybrid methods are proposed to better utilize their advantages.

Exact and Speedy Computation of Legendre Moments on Binary Images

A novel algorithm for the computation of Legendre moments, which ensures high accuracy and low computation time, is presented in this paper. The presented method exploits the compression capabilities, the image block representation exhibits. By describing the images with a set of homogenous blocks, keeping only the upper left and down right pixel coordinates, the long time consuming formulas used to compute Legendre moments, can be converted to more efficient ones. A typical comparison of the proposed method with the conventional one concludes to very impressive and promising results.

Human and Fire Detection from High Altitude UAV Images

Illegal migration as well as wildfires constitute commonplace situations in southern European countries, where the mountainous terrain and thick forests make the surveillance and location of these incidents a tall task. This territory could benefit from Unmanned Aerial Vehicles (UAVs) equipped with optical and thermal sensors in conjunction with sophisticated image processing and computer vision algorithms, in order to detect suspicious activity or prevent the spreading of a fire. Taking into account that the flight height is about to two kilometers, human and fire detection algorithms are mainly based on blob detection. For both processes thermal imaging is used in order to improve the accuracy of the algorithms, while in the case of human recognition information like movement patterns as well as shadow size and shape are also considered. For fire detection a blob detector is utilized in conjunction with a color based descriptor, applied to thermal and optical images, respectively. Unlike fire, human detection is a more demanding process resulting in a more sophisticated and complex algorithm. The main difficulty of human detection originates from the high flight altitude. In images taken from high altitude where the ground sample distance is not small enough, people appear as small blobs occupying few pixels, leading corresponding research works to be based on blob detectors to detect humans. Their shadows as well as motion detection and object tracking can then be used to determine whether these regions of interest do depict humans. This work follows this motif as well, nevertheless, its main novelty lies in the fact that the human detection process is adapted for high altitude and vertical shooting images in contrast with the majority of other similar works where lower altitudes and different shooting angles are considered. Additionally, in the interest of making our algorithms as fast as possible in order for them to be used in real time during the UAV flights, parallel image processing with the help of a specialized hardware device based on Field Programmable Gate Array (FPGA) is being worked on.

On accelerating the computation of 2-D Discrete Cosine Transform in image processing

A novel methodology that improves the computation rate of the 2-D discrete cosine transform (DCT) is proposed in this paper. By applying a new image decomposition scheme the image slice representation (ISR) followed by the image block representation (IBR) method, any gray-scale image can be described by a set of pixel blocks having certain intensity values. Based on this image representation, the computation of the 2-D DCT coefficients, useful for many image processing tasks, can be increased significantly. Appropriate experiments highlight the main advantages and establish the usefulness of the introduced method.