Modulating Shape Features by Color Attention for Object Recognition

Many previous studies have attempted to investigate the effect of visual cues on olfactory perception in humans. The majority of this research has only looked at the modulatory effect of color, which has typically been explained in terms of multisensory perceptual interactions. However, such crossmodal effects may equally well relate to interactions taking place at a higher level of information processing as well. In fact, it is well-known that semantic knowledge can have a substantial effect on people's olfactory perception. In the present study, we therefore investigated the influence of visual cues, consisting of color patches and/or shapes, on people's olfactory discrimination performance. Participants had to make speeded odor discrimination responses (lemon vs. strawberry) while viewing a red or yellow color patch, an outline drawing of a strawberry or lemon, or a combination of these color and shape cues. Even though participants were instructed to ignore the visual stimuli, our results demonstrate that the accuracy of their odor discrimination responses was influenced by visual distractors. This result shows that both color and shape information are taken into account during speeded olfactory discrimination, even when such information is completely task irrelevant, hinting at the automaticity of such higher level visual-olfactory crossmodal interactions.

It has been shown that integrating multiple cues will increase the reliability and robustness of a vision system in situations that no single cue is reliable. In this paper, we propose a method by fusing multiple cues (i.e., the color cue and the edge cue). In contrast to previous work, we propose a novel shape similarity measure which includes the spatial distribution of, the number of, and the gradient intensity of the edge points. We integrate this shape similarity measure with our recently proposed SMOG-based color similarity measure in the framework of particle filter (PF). Experimental results demonstrate the high robustness and effectiveness of our method in handling appearance changes, cluttered background, moving camera, and occlusions.

We studied the underlying neural mechanism of a simple choice behavior between competing alternatives in Drosophila. In a flight simulator, individual flies were conditioned to choose one of two flight paths in response to color and shape cues; after the training, they were tested with contradictory cues. Wild-type flies made a discrete choice that switched from one alternative to the other as the relative salience of color and shape cues gradually changed, but this ability was greatly diminished in mutant (mbm1) flies with miniature mushroom bodies or with hydroxyurea ablation of mushroom bodies. Thus, Drosophila genetics may be useful for elucidating the neural basis of choice behavior.

Image retrieval is the process of finding images in the database that are similar to the query image by measuring how close the feature values of the query image are to other images. Image retrieval is currently dominated by approaches that combine several different representations or features. The optimal weight of each feature is needed in combining the image features such as color features, texture features, and shape features. In this study, we use a multi-layer perceptron artificial neural network (MLP) method to obtain feature weights automatically and simultaneously look for optimal weights. The color moment is used to find nine color features, Gray Level Co-occurrence Matrix (GLCM) to find four texture features, and Hu Moment to find seven shape features totaling 20 neurons and all of these features become the input layer in our MLP network. Three neurons in output layers become the automatic weight of each feature. These weights are used to combine each feature's role in obtaining the relevant image. Euclidean Distance is used to measure similarity. The average precision values obtained using automatic feature weights are 93.94% for the synthetic dataset, 91.19% for the Coil-100 dataset, and 54.31% for the Wang dataset. These results have an average difference of 5.06% with the target so automatic feature weighting works well. This value is obtained at a hidden layer size of 11 and a learning rate of 0.1. In addition, the use of automatic feature weighting gives more accurate results compared to manual feature weighting.

Facial cues of adiposity play an important role in social perceptions, such as health and attractiveness judgments. Although relatively low levels of adiposity are generally associated with good health, low levels of adiposity are also a symptom of many communicable diseases. Consequently, it may be important to distinguish between individuals displaying low levels of facial adiposity because they are in good physical condition and those displaying low levels of facial adiposity because they are ill. Integrating information from facial cues of adiposity with information from other health cues, such as facial coloration, may facilitate such distinctions. Here, participants rated the health and attractiveness of face images experimentally manipulated to vary in shape cues of adiposity and color cues associated with perceived health. As we had predicted, the extent to which faces with low levels of adiposity were rated more positively than faces with relatively high levels of adiposity was greater for faces with healthy color cues than it was for faces with unhealthy color cues. Such interactions highlight the integrative processes that allow us to distinguish between healthy and unhealthy individuals during social interactions, potentially reducing the likelihood of contracting infectious diseases.

This paper describes approach to detect object using its shape and color information which is capable of detecting object rapidly and comparatively with good detection rate. This work divided into two part. First how to use color information to segment the object and secondly how to compare the contour of extracted object with contour of object to be the detected. Proposed method uses Fourier descriptor for detection of object. Experimental results on the detection of different objects verify the advantage of the proposed detection approach using shape information.

In this paper we examine two different automated video surveillance techniques for detection and tracking of pedestrians based on fusion of colour and thermal images. The first approach is a novel particle filtering based on Bayesian framework, and the seconf one is an approach based on fusion of shape and appearance cues. The shape and appearance based technique involves a layered two pass scheme, where in the first pass-an expectation-maximization (EM) algorithm is used to separate infrared images into still background and moving foreground layers. In the second pass: shape cues from the first pass is used to eliminate non-pedestrian moving objects and then appearance cue is used to locate the exact position of pedestrians. Then pedestrians are detected by sequential application of templates at multiple scales. For tracking the pedestrian a graph matching-based algorithm which fueses the shape and appearance information was used. The particle filtering based algorithm on other hand is based on building a scene background model with each pixel represented as a multimodal distribution of colour and thermal images. Then this background model is used to build a particle filter for tracking the pedestrian. The particle filter uses a novel formulation of observation likelihoods The evaluation of the two detection and tracking approaches was done by performing experiments on the thermal and colour dataset from OTCBVS databse.

Shape depiction in non-photorealistic rendering of 3D objects has mainly been concerned with the extraction of contour lines, which are generally detected by tracking the discontinuities of a given set of shape features varying on the surface and/or the picture plane. In this paper, we investigate another approach: the depiction of shape through shading. This technique is often used in scientific illustration, comics, cartoon animation and various other artwork. A common method consists in indirectly adapting light positions to reveal shape features; but it quickly becomes impractical when the complexity of the object augments. In contrast, our approach is to directly extract a set of shape cues that are easily manipulated by a user and re-introduced during shading. The main problem raised by such an approach is that shape cues must be identified in a continuous way in image space, as opposed to line-based techniques. Our solution is a novel view-dependent shape descriptor called Apparent Relief, which carries pertinent continuous shape cues for every pixel of an image. It consists of a combination of object- and imagespace attributes. Such an approach provides appealing properties: it is simple to manipulate by a user, may be applied to a vast range of styles, and naturally brings levels-of-detail functionalities. It is also simple to implement, and works in real-time on modern graphics hardware.

Line Extensions are among the most common form of product launch in packaged goods markets. As part of this process, brand managers must decide the visual design of the new variant’s packaging. To inform this decision making, this research aims to empirically quantify the efficacy of using colors versus images as signals of product variety on pack. We compare the use of color on 576 packs with perceptions of 1,853 category buyers across three categories in the USA. We find that for 84% of variant types, marketers use common colors to signal variety on pack, while consumers perceive that only 56% of variant types are represented by a particular color. Of greater concern, the colors used in practice and those expected by consumers align in only 16% of cases. By comparison, images are linked to variant types to a significantly greater extent (39% of cases). This suggests images are a stronger and more explicit signal of product variety than color. There are multiple implications arising from this study. It expands scholarly research on the use of colors in product extensions and, at the same time, provides a series of valuable benchmarks for industry practice in the portfolio management domain.

BackgroundImage analysis is the first crucial step to obtain reliable results from microarray experiments. First, areas in the image belonging to single spots have to be identified. Then, those target areas have to be partitioned into foreground and background. Finally, two scalar values for the intensities have to be extracted. These goals have been tackled either by spot shape methods or intensity histogram methods, but it would be desirable to have hybrid algorithms which combine the advantages of both approaches.ResultsA new robust and adaptive histogram type method is pixel clustering, which has been successfully applied for detecting and quantifying microarray spots. This paper demonstrates how the spot shape can be effectively integrated in this approach. Based on the clustering results, a bivalence mask is constructed. It estimates the expected spot shape and is used to filter the data, improving the results of the cluster algorithm. The quality measure 'stability' is defined and evaluated on a real data set. The improved clustering method is compared with the established Spot software on a data set with replicates.ConclusionThe new method presents a successful hybrid microarray image analysis solution. It incorporates both shape and histogram features and is specifically adapted to deal with typical microarray image characteristics. As a consequence of the filtering step pixels are divided into three groups, namely foreground, background and deletions. This allows a separate treatment of artifacts and their elimination from the further analysis.

Content Based Image Retrieval (CBIR) is important in computer aided plant species recognition. Texture and shape information have been the primitive image descriptors in content based image retrieval systems. This paper presents a novel framework for combining both the features, texture and shape information, and achieve higher retrieval efficiency. The study provides a methodology for retrieving medicinal plants images from a database of medicinal plant images based on shape and texture features. The shape descriptors include Zernike moment, Fourier descriptor (FD), Generic fourier Descriptor(GFD) and for texture descriptors gabor filters are used. The similarity measures, euclidean distance of each medicinal plant image from the database to query image is used. The images are sorted based on similarity of Euclidean distance. The retrieval experiments are carried on different training and test medicinal plant images. The effectiveness of different descriptors is confirmed by the experimental results. We have investigated shape and texture features for medicinal plant retrieval by successively combining the different transforms. The retrieval efficiency is reported through precision and recall rate. Experimental results by combining Gabor and Zernike transform outperforms the all other methods.

Many computer vision applications rely on matching features of a query image to reference data sets, but little work has explored how quickly data sets become out of date. In this paper we measure feature matching performance across 5 years of time-lapse data from 20 static cameras to empirically study how feature matching is affected by changing sunlight direction, seasons, weather, and the structural changes over time in outdoor settings. We identify several trends that may be relevant in real world applications: (1) features are much more likely to match within a few days of the reference data, (2) weather and sun-direction have a large effect on feature matching, and (3) there is a slow decay over time due to physical changes in a scene, but this decay is much smaller than effects of lighting direction and weather. These trends are consistent across standard choices for feature detection (DoG, MSER) and feature description (SIFT, SURF, and DAISY). Across all choices, analysis of the feature detection and matching pipeline highlights that performance decay is mostly due to failures in key point detection rather than feature description.

The lateral occipital complex (LOC) responds preferentially to objects compared with random stimuli or textures independent of the visual cue. However, it is unknown whether the LOC (or other cortical regions) are involved in the processing of edges or global surfaces without shape information. Here, we examined processing of 1) global shape, 2) disconnected edges without a global shape, and 3) global surfaces without edges versus random stimuli across motion and stereo cues. The LOC responded more strongly to global shapes than to edges, surfaces, or random stimuli, for both motion and stereo cues. However, its responses to local edges or global surfaces were not different from random stimuli. This suggests that the LOC processes shapes, not edges or surfaces. LOC also responded more strongly to objects than to holes with the same shape, suggesting sensitivity to border ownership. V7 responded more strongly to edges than to surfaces or random stimuli for both motion and stereo cues, whereas V3a and V4 preferred motion edges. Finally, a region in the caudal intraparietal sulcus (cIPS) responded more strongly to both stereo versus motion and to stereo surfaces versus random stereo (but not to motion surfaces vs. random motion). Thus we found evidence for cue-specific responses to surfaces in the cIPS, both cue-specific and cue-independent responses to edges in intermediate visual areas, and shape-selective responses across multiple cues in the LOC. Overall, these data suggest that integration of visual information across multiple cues is mainly achieved at the level of shape and underscore LOC's role in shape computations.

Person Re-Identification (Re-ID) is a challenging task with wide ranging applications in various fields. This paper presents a novel hand-crafted method for this issue, enhancing the state of the art ones in literature in two aspects. In contrast to most current studies that analyze texture features, we propose a discriminative and compact shape feature by applying Procrustes shape analysis. It not only retains shape distinctiveness of an individual sample, but also alleviates cross-view impacts. Furthermore, we combine the shape feature with some current popular texture features, namely LOMO and mid-level filters, so that the advantages of multiple clues can be jointly used. A score level fusion strategy is finally adopted to optimally integrate their credits. Evaluated on two public benchmarks, i.e. VIPeR and CUHK03, the proposed method achieves very competitive results, indicating its effectiveness in person Re-ID.

CEFEs: A CNN Explainable Framework for ECG Signals