Object Recognition with Features Inspired by Visual Cortex

Models of object recognition in cortex have so far been mostly applied to tasks involving the recognition of isolated objects presented on blank backgrounds. However, ultimately models of the visual system have to prove themselves in real world object recognition tasks. Here we took a first step in this direction: We investigated the performance of the HMAX model of object recognition in cortex recently presented by Riesenhuber & Poggio [1],[2] on the task of face detection using natural images. We found that the standard version of hmax performs rather poorly on this task, due to the low specificity of the hardwired feature set of C2 units in the model (corresponding to neurons in intermediate visual area V4) that do not show any particular tuning for faces vs. background. We show how visual features of intermediate complexity can be learned in HMAX using a simple learning rule. Using this rule, hmax outperforms a classical machine vision face detection system presented in the literature. This suggests an important role for the set of features in intermediate visual areas in object recognition.KeywordsObject RecognitionFace ImageFace DetectionBackground PatternBlank BackgroundThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Object categorization is a crucial cognitive ability. It has also received much attention in machine vision. However, the computational processes underlying object categorization in cortex are still poorly understood. In this paper we compare data recorded by Freedman et al. from monkeys to that of view-tuned units in our HMAX model of object recognition in cortex [],[]. We FInd that the results support a model of object recognition in cortex [] in which a population of shape-tuned neurons responding to individual exemplars provides a general basis for neurons tuned to different recognition tasks. Simulations further indicate that this strategy of first learning a general but object class-specific representation as input to a classifier simplifies the learning task. Indeed, the physiological data suggest that in the monkey brain, categorization is performed by PFC neurons performing a simple classification based on the thresholding of a linear sum of the inputs from examplar-tuned units. Such a strategy has various computational advantages, especially with respect to transfer across novel recognition tasks.

The neural mechanisms underlying object recognition in cluttered scenes (i.e., containing more than one object) remain poorly understood. Studies have suggested that neural responses to multiple objects correspond to an average of the responses to the constituent objects. Yet, it is unclear how the identities of an unknown number of objects could be disentangled from a confounded average response. Here, we use a popular computational biological vision model to show that averaging-like responses can result from responses of clutter-tolerant neurons to suboptimal stimuli. The model also provides a novel prediction, that human detection ability should show a U-shaped dependency on target-clutter similarity, which is confirmed experimentally, supporting a simple, unifying account of how the brain performs object recognition in clutter.

Aurora is the typical ionosphere track generated by the interaction of solar wind and magnetosphere, whose modality and variation are significant to the study of space weather activity. A new aurora classification algorithm based on biologically inspired features (BIFs) and discriminative locality alignment (DLA) is proposed in this paper. First, an aurora image is represented by the BIFs, which combines the C1 units from the hierarchical model of object recognition in cortex and the gist features from the saliency map; then, the manifold learning method called DLA is used to obtain the effective sparse representation for auroras based on BIFs; finally, classification results using support vector machine and nearest neighbour with three sets of features: the C1 unit features, the gist features and the BIFs illustrate the effectiveness and robustness of our method on the real aurora image database from Chinese Arctic Yellow River Station.

Event Abstract Back to Event Logarithmic Hybrid Optical Neural Network-type systems: towards digital-optical cognitive models of robust object recognition Ioannis Kypraios1* 1 Oxford University, Centre for Innovation & Enterprise, APEM Computing Lab, United Kingdom Abstract - By combining the complex logarithmic r-theta mapping of a space-variant imaging sensor [1, 2] with the hybrid digital-optical neural network filter together with a window unit multiple objects of the same class or of different classes can robustly be recognized. The resulted logarithmic r-theta mapping for hybrid digital-optical neural network system or briefly referred to as logarithmic hybrid optical neural network system is shown to exhibit with a single pass over the input data simultaneously in-plane rotation, out-of-plane rotation, scale, log r-θ map translation and shift invariance, and good clutter tolerance by recognizing correctly the different objects within the cluttered scenes. Here, we study the biologically-inspired knowledge learning and knowledge representation [3] achieved by the logarithmic hybrid optical neural network-type of object recognition systems (see Fig. 1 and Fig. 2). We investigate the effects that altering the knowledge representation can have on the problem’s learned knowledge and the problem solving process, in overall. Further, we study the logarithmic unconstrained-, logarithmic constrained-, and logarithmic modified-hybrid optical neural network systems architectures’ designs [4, 5]. We show how the logarithmic unconstrained-hybrid optical neural network object recognition system applies an unconstrained representation of the problem’s knowledge to maximize the search of solutions, how the logarithmic constrained-hybrid optical neural network object recognition system uses a constrained representation of the problem’s knowledge to guide the search towards certain solutions over others in the multidimensional search space, and how the logarithmic modified-hybrid optical neural network object recognition system uses memory-like masks to recall certain solutions over others in the multidimensional search space. Fig. 1. (a) Simplified human retina and visual cortex model used for description purposes only; (b) A digital-optical computational model for the cognitive interaction between the retina and the human visual cortex with the general logarithmic hybrid optical neural network architercture. Fig. 2. Biologically-inspired knowledge learning and knowledge representation with the logarithmic hybrid optical neural network-type of object recognition systems. Figure 1 Figure 2 References [1] C. F. R. Weiman, “Video compression via log-polar mapping”, Real-Time Image Processing II, SPIE Symposium on OE/Aerospace Sensing, Vol. 1295, 266-277 (1990) [2] C. G. Ho et al., “Sensor geometry and sampling methods for space-variant image processing”, Pattern Analysis and Applications, Vol. 5, 369-384 (2002) [3] I. Lee, and B. Portier, "An empirical study of knowledge representation and learning within conceptual spaces for intelligent agents", 6th IEEE/ACIS International Conference Computer and Information Science, 463-468, Melbourne, Australia (2007) [4] I. Kypraios et al., “Fully invariant complex Logarithmic r- map for the Hybrid Optical Neural Network filter for object recognition within cluttered scenes”, 50th Anniversary International Symposium ELMAR 2008, IEEE Region 8/IEEE Croatia Section/EURASIP, Zadar-Croatia, Vol. 1, 141-146 (2008) [5] I. Kypraios et al., “Logarithmic r-θ mapping for hybrid optical neural network filter for object recogntion within cluttered scenes”, Recent Advances in Multimedia Signal Processing and Communications, SCI231, Springer-Verlag Berlin Heidelberg, 91-120 (2009) Keywords: digital-optical, cognitive, object recognition, Robust and Adaptive Systems, Knowledge representation, learning and memory Conference: Neuroinformatics 2013, Stockholm, Sweden, 27 Aug - 29 Aug, 2013. Presentation Type: Poster Topic: Neuromorphic engineering Citation: Kypraios I (2013). Logarithmic Hybrid Optical Neural Network-type systems: towards digital-optical cognitive models of robust object recognition. Front. Neuroinform. Conference Abstract: Neuroinformatics 2013. doi: 10.3389/conf.fninf.2013.09.00066 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 09 Apr 2013; Published Online: 11 Jul 2013. * Correspondence: Dr. Ioannis Kypraios, Oxford University, Centre for Innovation & Enterprise, APEM Computing Lab, Begbroke, Oxfordshire, OX5 1PF, United Kingdom, ioanniskyp@yahoo.com Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Ioannis Kypraios Google Ioannis Kypraios Google Scholar Ioannis Kypraios PubMed Ioannis Kypraios Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

THINGS-data reflects three large-scale neuroimaging and behavioral datasets of object processing in humans, comprising densely sampled functional MRI and magnetoencephalographic recordings, as well as 4.70 million similarity judgments in response to thousands of photographic images for up to 1854 objects.

In picture processing, picture segmentation, object classification and recognition is an impressive concept in present days because of increasing computer vision applications in real time applications. Based on required application, divide a picture into particular relevant clusters based on equivalent partitioning. Object identification is a minimum work to identify objects in a given picture or video with pixel values. The main representation of object classification from a given picture is to detect picture instances with respect to categorization of object. Object recognition is a complex task, when the pictures are poor quality, occlusion, and noise and in picture with background cutter sequences, this becomes more and efficient challenging task in picture processing. To appear object categorization and recognition effectively in pictures, there are several methods and approaches were introduced to solve object representation effectively. In this paper we review the different techniques of contextual feature extraction with respect to picture information of object classification, categorization and recognition of scalability and optimizations in real time picture processing applications. Our research gives better review of different approaches in picture categorization.

Deep neural networks (DNNs) are promising models of the cortical computations supporting human object recognition. However, despite their ability to explain a significant portion of variance in neural data, the agreement between models and brain representational dynamics is far from perfect. We address this issue by asking which representational features are currently unaccounted for in neural time series data, estimated for multiple areas of the ventral stream via source-reconstructed magnetoencephalography data acquired in human participants (nine females, six males) during object viewing. We focus on the ability of visuo-semantic models, consisting of human-generated labels of object features and categories, to explain variance beyond the explanatory power of DNNs alone. We report a gradual reversal in the relative importance of DNN versus visuo-semantic features as ventral-stream object representations unfold over space and time. Although lower-level visual areas are better explained by DNN features starting early in time (at 66 ms after stimulus onset), higher-level cortical dynamics are best accounted for by visuo-semantic features starting later in time (at 146 ms after stimulus onset). Among the visuo-semantic features, object parts and basic categories drive the advantage over DNNs. These results show that a significant component of the variance unexplained by DNNs in higher-level cortical dynamics is structured and can be explained by readily nameable aspects of the objects. We conclude that current DNNs fail to fully capture dynamic representations in higher-level human visual cortex and suggest a path toward more accurate models of ventral-stream computations.SIGNIFICANCE STATEMENT When we view objects such as faces and cars in our visual environment, their neural representations dynamically unfold over time at a millisecond scale. These dynamics reflect the cortical computations that support fast and robust object recognition. DNNs have emerged as a promising framework for modeling these computations but cannot yet fully account for the neural dynamics. Using magnetoencephalography data acquired in human observers during object viewing, we show that readily nameable aspects of objects, such as 'eye', 'wheel', and 'face', can account for variance in the neural dynamics over and above DNNs. These findings suggest that DNNs and humans may in part rely on different object features for visual recognition and provide guidelines for model improvement.

Aiming at the object recognition through UAV, an intelligent object recognition model based on YOLO and Generative adversarial network is proposed in this paper. Firstly, the solution is given, and an object recognition model that can realize intelligent recognition is established. Then, in order to improve the resolution of the identified images, an image resolution enhancement model based on generative adversarial networks is built. After that, the structure and parameters of the recognition model and image resolution enhancement model are adjusted through the simulation experiments to improve the accuracy and robustness of the object recognition. Finally, the object recognition model based on YOLO and generative adversarial network in this paper is verified through UAV.

Everyday vision requires robustness to a myriad of environmental factors that degrade stimuli. Foreground clutter can occlude objects of interest, and complex lighting and shadows can decrease the contrast of items. How does the brain recognize visual objects despite these low-quality inputs? On the basis of predictions from a model of object recognition that contains excitatory feedback, we hypothesized that recurrent processing would promote robust recognition when objects were degraded by strengthening bottom-up signals that were weakened because of occlusion and contrast reduction. To test this hypothesis, we used backward masking to interrupt the processing of partially occluded and contrast reduced images during a categorization experiment. As predicted by the model, we found significant interactions between the mask and occlusion and the mask and contrast, such that the recognition of heavily degraded stimuli was differentially impaired by masking. The model provided a close fit of these results in an isomorphic version of the experiment with identical stimuli. The model also provided an intuitive explanation of the interactions between the mask and degradations, indicating that masking interfered specifically with the extensive recurrent processing necessary to amplify and resolve highly degraded inputs, whereas less degraded inputs did not require much amplification and could be rapidly resolved, making them less susceptible to masking. Together, the results of the experiment and the accompanying model simulations illustrate the limits of feedforward vision and suggest that object recognition is better characterized as a highly interactive, dynamic process that depends on the coordination of multiple brain areas.

Attention to distinguishing features in object recognition: An interactive-iterative framework

For decades, the brain's visual pathway has inspired machine and deep learning models, yet these models oversimplify the brain’s complex visual processing. This is manifested in the significant superiority of the brain in comparison to the developed models in terms of the accuracy and the amount of data needed for training. Therefore, rather than using the brain as an inspiration, in this paper, we introduce Img2Neuro; a Convolutional Neural Network (CNN) model feature extractor that predicts the visual brain's response to images by encoding neural activity. Img2Neuro is trained on natural scene images paired with single-neuron recordings from the visual cortex and thalamus of mice and monkeys. We explore the feasibility of using Img2Neuro as a feature extractor for object recognition, where the output of Img2Neuro in response to unseen images is used as input to classifiers with the task of recognizing the object in the image. We evaluated our approach on three benchmark datasets; namely, MNIST, Fashion-MNIST, and Cifar10. In our experiments, we examined the classification performance when Img2Neuro is used as a feature extractor compared to using the images as direct input to the classifier, using five different classifiers; namely, linear discriminant analysis, perceptron, logistic regression, ridge classifier, and a single-layer neural network. The results demonstrate superior performance when using Img2Neuro in most datasets and across all classifiers, reaching an enhancement in accuracy of 9% on the MNIST dataset, 2% on FashionMNIST, and 18% on Cifar10 in some cases compared to using raw images as an input in the classifiers. The performance enhancements suggest that brain-trained encoders can effectively capture image features for object recognition tasks. By leveraging neural response data, Img2Neuro demonstrates a promising avenue for bridging the gap between biological and artificial visual processing, ultimately leading to novel strategies for improving state-of-the-art object recognition models.

There is substantial evidence for individual differences in personality and cognitive abilities, but we lack clear intuitions about individual differences in visual abilities. Previous work on this topic has typically compared performance with only 2 categories, each measured with only 1 task. This approach is insufficient for demonstration of domain-general effects. Most previous work has used familiar object categories, for which experience may vary between participants and categories, thereby reducing correlations that would stem from a common factor. In Study 1, we adopted a latent variable approach to test for the first time whether there is a domain-general object recognition ability, o. We assessed whether shared variance between latent factors representing performance for each of 5 novel object categories could be accounted for by a single higher-order factor. On average, 89% of the variance of lower-order factors denoting performance on novel object categories could be accounted for by a higher-order factor, providing strong evidence for o. Moreover, o also accounted for a moderate proportion of variance in tests of familiar object recognition. In Study 2, we assessed whether the strong association across categories in object recognition is due to third-variable influences. We find that o has weak to moderate associations with a host of cognitive, perceptual, and personality constructs and that a clear majority of the variance in and covariance between performance on different categories is independent of fluid intelligence. This work provides the first demonstration of a reliable, specific, and domain-general object recognition ability, and suggest a rich framework for future work in this area. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Object recognition is of fundamental importance in computer vision. In a few years, pedestrian detection, car detection, and more generally scene recognition will likely be reliable enough to allow fully-automated car navigation, and the human driver will be relegated to the back seat to sip his coffee. In this thesis we are interested in recognizing individual objects and categories. In order to reduce the volume of information one has to process, images are characterized by sets of features. These features, also called interest points, are targeted at image locations with high local information content. Various systems for detecting interest points and for describing the local image appearance near these points, have been proposed in the last two decades. We investigate which combinations from this plethora of detectors and descriptors, are most suited for object recognition tasks. On to the problem of object recognition, we are first interested in recognizing individual objects. In a few years, one can imagine that customers in shops, will take with their cell phone a picture of a product that looks interesting, send it to a remote server with a huge database of individual objects, and get back information about that specific product. We propose a system for individual object recognition, inspired from previous work on coarse-to-fine recognition. All steps of the recognition process are translated into principled probabilistic terms, which allows us to outperform a state-of-the-art commercial system for individual recognition. Regarding categories, faces are probably the category that has received the most attention in computer vision literature. Here we propose a system to recognize images of the same individual in large databases of images. This can be of high interest when looking for images of a given person over the internet. Our method's advantage is that it works on real-world images, as opposed to the face databases from the literature, collected in laboratories with controlled lighting, pose and background conditions. Finally, we are interested in recognition of object categories in general. Using support vector machines for the classification task, we propose a features-based kernel that improves recognition performance on object categories.

Lightweight object detection and recognition models are extremely crucial for in-orbit applications, which is the most critical factor for whether deep learning-based object detection and recognition algorithms can be applied to remote sensing satellites for real-time or near real-time processing. Global information is extremely important for object detection and recognition of remote sensing images. However, due to the high computational cost, the existing CNN-based lightweight models over-emphasize on the extraction of local information, while ignoring the global information. For this reason, we propose a lightweight object detection and recognition model (Lightweight Global-Local Detection, LGLDet) based on the especially light global modeling structure. In LGLDet, light global-local module (LGLM) is proposed to extract the global and local information. The LGLM consists of Point2Patch Non-Local (P2PNL), local branch and skip connection. Specifically, P2PNL is proposed to reduce the computation of global long-range dependency modeling. In addition, the feature fusion part and detection head are also designed in a lightweight way. In the experiments, the proposed method can achieve optimal performance with fewer parameters and lower computational complexity than existing CNN-based lightweight models and transformer-based lightweight models with similar parameters or computational complexity. The code will be released on the site of https://github.com/dyl96/LGLDet.