Detection of matchings in a sequence of underwater images through texture analysis

This paper presents an approach to ameliorate the reliability of the correspondence points relating two consecutive images of a sequence. The images are especially difficult to handle, since they have been acquired by a camera looking at the sea floor while carried by an underwater robot. Underwater images are usually difficult to process due to light absorption, changing image radiance and lack of well-defined features. A new approach based on gray-level region matching and selective texture analysis significantly improves the matching reliability

Active regions for colour texture segmentation integrating region and boundary information

In this paper a colour texture segmentation method, which unifies region and boundary information, is proposed. The algorithm uses a coarse detection of the perceptual (colour and texture) edges of the image to adequately place and initialise a set of active regions. Colour texture of regions is modelled by the conjunction of non-parametric techniques of kernel density estimation (which allow to estimate the colour behaviour) and classical co-occurrence matrix based texture features. Therefore, region information is defined and accurate boundary information can be extracted to guide the segmentation process. Regions concurrently compete for the image pixels in order to segment the whole image taking both information sources into account. Furthermore, experimental results are shown which prove the performance of the proposed method

Image segmentation integrating colour, texture and boundary information

La tesis se centra en la Visión por Computador y, más concretamente, en la segmentación de imágenes, la cual es una de las etapas básicas en el análisis de imágenes y consiste en la división de la imagen en un conjunto de regiones visualmente distintas y uniformes considerando su intensidad, color o textura. Se propone una estrategia basada en el uso complementario de la información de región y de frontera durante el proceso de segmentación, integración que permite paliar algunos de los problemas básicos de la segmentación tradicional. La información de frontera permite inicialmente identificar el número de regiones presentes en la imagen y colocar en el interior de cada una de ellas una semilla, con el objetivo de modelar estadísticamente las características de las regiones y definir de esta forma la información de región. Esta información, conjuntamente con la información de frontera, es utilizada en la definición de una función de energía que expresa las propiedades requeridas a la segmentación deseada: uniformidad en el interior de las regiones y contraste con las regiones vecinas en los límites. Un conjunto de regiones activas inician entonces su crecimiento, compitiendo por los píxeles de la imagen, con el objetivo de optimizar la función de energía o, en otras palabras, encontrar la segmentación que mejor se adecua a los requerimientos exprsados en dicha función. Finalmente, todo esta proceso ha sido considerado en una estructura piramidal, lo que nos permite refinar progresivamente el resultado de la segmentación y mejorar su coste computacional. La estrategia ha sido extendida al problema de segmentación de texturas, lo que implica algunas consideraciones básicas como el modelaje de las regiones a partir de un conjunto de características de textura y la extracción de la información de frontera cuando la textura es presente en la imagen. Finalmente, se ha llevado a cabo la extensión a la segmentación de imágenes teniendo en cuenta las propiedades de color y textura. En este sentido, el uso conjunto de técnicas no-paramétricas de estimación de la función de densidad para la descripción del color, y de características textuales basadas en la matriz de co-ocurrencia, ha sido propuesto para modelar adecuadamente y de forma completa las regiones de la imagen. La propuesta ha sido evaluada de forma objetiva y comparada con distintas técnicas de integración utilizando imágenes sintéticas. Además, se han incluido experimentos con imágenes reales con resultados muy positivos.

Texture recognition under varying imaging geometries

La visió és probablement el nostre sentit més dominant a partir del qual derivem la majoria d'informació del món que ens envolta. A través de la visió podem percebre com són les coses, on són i com es mouen. En les imatges que percebem amb el nostre sistema de visió podem extreure'n característiques com el color, la textura i la forma, i gràcies a aquesta informació som capaços de reconèixer objectes fins i tot quan s'observen sota unes condicions totalment diferents. Per exemple, som capaços de distingir un mateix objecte si l'observem des de diferents punts de vista, distància, condicions d'il·luminació, etc. La Visió per Computador intenta emular el sistema de visió humà mitjançant un sistema de captura d'imatges, un ordinador, i un conjunt de programes. L'objectiu desitjat no és altre que desenvolupar un sistema que pugui entendre una imatge d'una manera similar com ho realitzaria una persona. Aquesta tesi es centra en l'anàlisi de la textura per tal de realitzar el reconeixement de superfícies. La motivació principal és resoldre el problema de la classificació de superfícies texturades quan han estat capturades sota diferents condicions, com ara distància de la càmera o direcció de la il·luminació. D'aquesta forma s'aconsegueix reduir els errors de classificació provocats per aquests canvis en les condicions de captura. En aquest treball es presenta detalladament un sistema de reconeixement de textures que ens permet classificar imatges de diferents superfícies capturades en diferents condicions. El sistema proposat es basa en un model 3D de la superfície (que inclou informació de color i forma) obtingut mitjançant la tècnica coneguda com a 4-Source Colour Photometric Stereo (CPS). Aquesta informació és utilitzada posteriorment per un mètode de predicció de textures amb l'objectiu de generar noves imatges 2D de les textures sota unes noves condicions. Aquestes imatges virtuals que es generen seran la base del nostre sistema de reconeixement, ja que seran utilitzades com a models de referència per al nostre classificador de textures. El sistema de reconeixement proposat combina les Matrius de Co-ocurrència per a l'extracció de característiques de textura, amb la utilització del Classificador del veí més proper. Aquest classificador ens permet al mateix temps aproximar la direcció d'il·luminació present en les imatges que s'utilitzen per testejar el sistema de reconeixement. És a dir, serem capaços de predir l'angle d'il·luminació sota el qual han estat capturades les imatges de test. Els resultats obtinguts en els diferents experiments que s'han realitzat demostren la viabilitat del sistema de predicció de textures, així com del sistema de reconeixement.

Effect of combined heat and high-pressure treatments on the texture of chicken breast muscle (Pectoralis fundus)

Commercially supplied chicken breast muscle was subjected to simultaneous heat and pressure treatments. Treatment conditions ranged from ambient temperature to 70 °C and from 0.1 to 800 MPa, respectively, in various combinations. Texture profile analysis (TPA) of the treated samples was performed to determine changes in muscle hardness. At treatment temperatures up to and including 50 °C, heat and pressure acted synergistically to increase muscle hardness. However, at 60 and 70 °C, hardness decreased following treatments in excess of 200 MPa. TPA was performed on extracted myofibrillar protein gels that after treatment under similar conditions revealed similar effects of heat and pressure. Differential scanning calorimetry analysis of whole muscle samples revealed that at ambient pressure the unfolding of myosin was completed at 60 °C, unlike actin, which completely denatured only above 70 °C. With simultaneous pressure treatment at >200 MPa, myosin and actin unfolded at 20 °C. Unfolding of myosin and actin could be induced in extracted myofibrillar protein with simultaneous treatment at 200 MPa and 40 °C. Electrophoretic analysis indicated high pressure/temperature regimens induced disulfide bonding between myosin chains.

Texture development in ice cream - effects of adding cocoa solids

Dynamic rheological techniques can aid the understanding of the factors contributing to ice cream structure, though the data obtained differs from that deduced from destructive techniques. Studies have shown that ice cream systems are both strain- and frequency-dependent. Chocolate ice cream is normally more viscous than the equivalent vanilla ice cream during mix preparation and has more body on freezing. Ice creams were prepared with and without cocoa solids and frequency sweeps were made from 0.1 to 100 Hz at 0.1% strain. With rapidly frozen ice creams, both G' and G" increased in the presence of cocoa solids. Comparison of mixes made with and without low-fat cocoa powder or non-gelatinizing starch demonstrated a similar relationship, with higher apparent viscosities in those mixes containing either cocoa powder or the starch. The results were consistent with the cocoa particles adding to the effect of the fat globules in increasing viscosity.

Composition, color, and texture of Thai indigenous and broiler chicken muscles

Chemical compositions and physical properties of mixed-sex Thai indigenous (Gallus domesticus) and broiler (commercial breed, CP707) chicken biceps femoris and pectoralis muscles were determined. Indigenous chicken muscles contained higher protein contents but lower fat and ash contents compared to broiler muscles (P < 0.001). The amino acid profile of the indigenous chicken muscles was similar to that of the broiler muscles except they were slightly richer in glutamic acid (P < 0.05). The indigenous chicken muscles contained more saturated and less polyunsaturated fatty acids than the broiler muscles. There were no differences in the monounsaturated fatty acid contents between the breeds. The total collagen contents of indigenous pectoralis and biceps femoris muscles were 5.09 and 12.85 mg/g, respectively, which were higher than those found in broiler pectoralis (3.86 mg/g) and biceps femoris muscles (8.70 mg/g) (P < 0.001). Soluble collagen contents were lower for indigenous pectoralis and biceps femoris muscles, 22.16 vs. 31.38% and 26.06 vs. 33.87%, respectively. The CIE system values of lightness (L*), redness (a*), and yellowness (b*) of indigenous chicken muscles were higher than those of broiler muscles. The shear values of indigenous chicken muscles either raw or cooked were higher than those of broiler muscles (P < 0.05). After cooking, the shear values decreased for broiler biceps femoris and pectoralis muscles (P < 0.05), whereas no change was observed for indigenous chicken biceps femoris muscle (P > 0.05). Shear values increased for indigenous chicken pectoralis muscle (P < 0.05).

Effect of heat treatment on changes in texture, structure and properties of Thai indigenous chicken muscle

Changes in texture, microstructure, colour and protein solubility of Thai indigenous and broiler chicken Pectoralis muscle stripes cooked at different temperatures were evaluated. The change in shear value of both chicken muscles was a significant increase from 50 to 80 degrees C but no change from 80 to 100 degrees C. A significant decrease in fibre diameter was obtained in samples heated to an internal temperature of 60 degrees C and the greatest shrinkage of sarcomeres was observed with internal temperatures of 70-100 and 80-100 C for broiler and indigenous chicken muscles, respectively (P < 0.05). Cooking losses of indigenous chicken muscles increased markedly in the temperature range 80-100 C and were significantly higher than those of the broiler (P < 0.001). With increasing temperature, from 50 to 70 degrees C, cooked chicken muscle became lighter and yellower. Relationships between changes in sarcomere length, fibre diameter, shear value, cooking loss and solubility of muscle proteins were evaluated. It was found that the solubility of muscle protein was very highly correlated with the texture of cooked broiler muscle while sarcomere length changes and collagen solubility were important factors influencing the cooking loss and texture of cooked indigenous chicken muscle. (c) 2004 Elsevier Ltd. All rights reserved.

High pressure/thermal treatment effects on the texture of beef muscle

The effects of high pressure (to 800 MPa) applied at different temperatures (20-70 degreesC) for 20 min on beef post-rigor longissimus dorsi texture were studied. Texture profile analysis showed that when heated at ambient pressure there was the expected increase in hardness with increasing temperature and when pressure was applied at room temperature there was again the expected increase in hardness with increasing pressure. Similar results to those found at ambient temperature were found when pressure was applied at 40 degreesC. However, at higher temperatures, 60 and 70 degreesC it was found that pressures of 200 MPa caused large and significant decreases in hardness. The results found for hardness were mirrored by those for gumminess and chewiness. To further understand the changes in texture observed, intact beef longissimus dorsi samples and extracted myofibrils were both subjected to differential scanning calorimetry after being subjected to the same pressure/temperature regimes. As expected collagen was reasonably inert to pressure and only at temperatures of 60-70 degreesC was it denatured/unfolded. However, myosin was relatively easily unfolded by both pressure and temperature and when pressure denatured a new and modified structure was formed of low thermal stability. Although this new structure had low thermal stability at ambient pressure it still formed in both the meat and myofibrils when pressure was applied at 60 degreesC. It seems unlikely that structurally induced changes can be a major cause of the significant loss of hardness observed when beef is treated at high temperature (60-70 degreesC) and 200 MPa and it is suggested that accelerated proteolysis under these conditions is the major cause. (C) 2004 Elsevier Ltd. All rights reserved.

Texture segmentation in Williams syndrome

Williams syndrome (WS) is a developmental disorder in which visuo-spatial cognition is poor relative to verbal ability. At the level of visuo-spatial perception, individuals with WS can perceive both the local and global aspects of an image. However, the manner in which local elements are integrated into a global whole is atypical, with relative strengths in integration by luminance, closure, and alignment compared to shape, orientation and proximity. The present study investigated the manner in which global images are segmented into local parts. Segmentation by seven gestalt principles was investigated: proximity, shape, luminance, orientation, closure, size (and alignment: Experiment I only). Participants were presented with uniform texture squares and asked to detect the presence of a discrepant patch (Experiment 1) or to identify the form of a discrepant patch as a capital E or H (Experiment 2). In Experiment 1, the pattern and level of performance of the WS group did not differ from that of typically developing controls, and was commensurate with the general level of non-verbal ability observed in WS. These results were replicated in Experiment 2, with the exception of segmentation by proximity, where individuals with WS demonstrated superior performance relative to the remaining segmentation types. Overall, the results suggest that, despite some atypical aspects of visuo-spatial perception in WS, the ability to segment a global form into parts is broadly typical in this population. In turn, this informs predictions of brain function in WS, particularly areas V1 and V4. (c) 2006 Elsevier Ltd. All rights reserved.

Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms

Objective: This paper presents a detailed study of fractal-based methods for texture characterization of mammographic mass lesions and architectural distortion. The purpose of this study is to explore the use of fractal and lacunarity analysis for the characterization and classification of both tumor lesions and normal breast parenchyma in mammography. Materials and methods: We conducted comparative evaluations of five popular fractal dimension estimation methods for the characterization of the texture of mass lesions and architectural distortion. We applied the concept of lacunarity to the description of the spatial distribution of the pixel intensities in mammographic images. These methods were tested with a set of 57 breast masses and 60 normal breast parenchyma (dataset1), and with another set of 19 architectural distortions and 41 normal breast parenchyma (dataset2). Support vector machines (SVM) were used as a pattern classification method for tumor classification. Results: Experimental results showed that the fractal dimension of region of interest (ROIs) depicting mass lesions and architectural distortion was statistically significantly lower than that of normal breast parenchyma for all five methods. Receiver operating characteristic (ROC) analysis showed that fractional Brownian motion (FBM) method generated the highest area under ROC curve (A z = 0.839 for dataset1, 0.828 for dataset2, respectively) among five methods for both datasets. Lacunarity analysis showed that the ROIs depicting mass lesions and architectural distortion had higher lacunarities than those of ROIs depicting normal breast parenchyma. The combination of FBM fractal dimension and lacunarity yielded the highest A z value (0.903 and 0.875, respectively) than those based on single feature alone for both given datasets. The application of the SVM improved the performance of the fractal-based features in differentiating tumor lesions from normal breast parenchyma by generating higher A z value. Conclusion: FBM texture model is the most appropriate model for characterizing mammographic images due to self-affinity assumption of the method being a better approximation. Lacunarity is an effective counterpart measure of the fractal dimension in texture feature extraction in mammographic images. The classification results obtained in this work suggest that the SVM is an effective method with great potential for classification in mammographic image analysis.

Classification-based probabilistic modeling of texture transition for fast line search tracking and delineation

We introduce a classification-based approach to finding occluding texture boundaries. The classifier is composed of a set of weak learners, which operate on image intensity discriminative features that are defined on small patches and are fast to compute. A database that is designed to simulate digitized occluding contours of textured objects in natural images is used to train the weak learners. The trained classifier score is then used to obtain a probabilistic model for the presence of texture transitions, which can readily be used for line search texture boundary detection in the direction normal to an initial boundary estimate. This method is fast and therefore suitable for real-time and interactive applications. It works as a robust estimator, which requires a ribbon-like search region and can handle complex texture structures without requiring a large number of observations. We demonstrate results both in the context of interactive 2D delineation and of fast 3D tracking and compare its performance with other existing methods for line search boundary detection.

Interaction of visual and haptic information in simulated environments: texture perception

This paper describes experiments relating to the perception of the roughness of simulated surfaces via the haptic and visual senses. Subjects used a magnitude estimation technique to judge the roughness of “virtual gratings” presented via a PHANToM haptic interface device, and a standard visual display unit. It was shown that under haptic perception, subjects tended to perceive roughness as decreasing with increased grating period, though this relationship was not always statistically significant. Under visual exploration, the exact relationship between spatial period and perceived roughness was less well defined, though linear regressions provided a reliable approximation to individual subjects’ estimates.