Recognition Of Common Objects Research Articles

Innovation in Transparent Technology with a Deep Dive into Iot-Connected Smart Glass

The goal of the project "Innovation In Transparent Technology With A Deep Dive Into IoT-Connected Smart Glass" using YOLO Image Processing is to create a cutting-edge assistive technology solution that will increase the mobility and freedom of people who are blind or visually impaired. The goal of this project is to incorporate wearable smart glasses with real-time object recognition utilizing the YOLO (You Only Look Once) algorithm. The Arduino Nano microprocessor, buzzer, and sensors that are built into the smart glasses will allow for the real-time recognition of common objects and obstacles within the user's surroundings. The system will use an easy-to-use, accessible user interface to communicate detected objects and navigation hints to the user through buzzer and vibration.

OW-Adapter: Human-Assisted Open-World Object Detection with a Few Examples.

Open-world object detection (OWOD) is an emerging computer vision problem that involves not only the identification of predefined object classes, like what general object detectors do, but also detects new unknown objects simultaneously. Recently, several end-to-end deep learning models have been proposed to address the OWOD problem. However, these approaches face several challenges: a) significant changes in both network architecture and training procedure are required; b) they are trained from scratch, which can not leverage existing pre-trained general detectors; c) costly annotations for all unknown classes are needed. To overcome these challenges, we present a visual analytic framework called OW-Adapter. It acts as an adaptor to enable pre-trained general object detectors to handle the OWOD problem. Specifically, OW-Adapter is designed to identify, summarize, and annotate unknown examples with minimal human effort. Moreover, we introduce a lightweight classifier to learn newly annotated unknown classes and plug the classifier into pre-trained general detectors to detect unknown objects. We demonstrate the effectiveness of our framework through two case studies of different domains, including common object recognition and autonomous driving. The studies show that a simple yet powerful adaptor can extend the capability of pre-trained general detectors to detect unknown objects and improve the performance on known classes simultaneously.

Visuo-haptic transfer for object recognition in children with peripheral visual impairment

It is well known how early visual experience is critical for the development of multisensory processing abilities, and for this reason an early vision impairment could hinder the transfer of different sensory information during the exploration and recognition of the surrounding environment. Recently, we verified that visuo-haptic transfer for object recognition emerges early in typically developing children but matures slowly during the school-age period. Subsequently we verified the presence of a slower trend of development in unisensory and multisensory skills in children with early abnormal motor and sensory experiences due to brain lesions. Now, we investigated unimodal visual information, unimodal haptic information and visuo-haptic information transfer in children with a diagnosis of low-vision, due to congenital visual impairment. Unimodal and bimodal processes for object recognition were explored in 11 children with low-vision and the results were matched with those of 22 controls. Participants were tested using a clinical protocol involving visual exploration of black-and-white photographs of common objects, haptic exploration of real objects and visuo-haptic transfer of these two types of information. Results show a normal development in haptic unisensory processing in children with low vision and a significant difference in multisensory transfer between the two groups. In children with visual impairment, multisensory processes do not facilitate the recognition of common objects as in typical children, probably because early visual impairment may impact the cross-sensory calibration of vision and touch.

PennSyn2Real: Training Object Recognition Models Without Human Labeling

Scalable training data generation is a critical problem in deep learning. We propose PennSyn2Real - a photo-realistic synthetic dataset consisting of more than 100 000 4K images of more than 20 types of micro aerial vehicles (MAVs). The dataset can be used to generate arbitrary numbers of training images for high-level computer vision tasks such as MAV detection and classification. Our data generation framework bootstraps chroma-keying, a mature cinematography technique, with a motion tracking system providing artifact-free and curated annotated images. Our system, therefore, allows object orientations and lighting to be controlled. This framework is easy to set up and can be applied to a broad range of objects, reducing the gap between synthetic and real-world data. We show that synthetic data generated using this framework can be directly used to train CNN models for common object recognition tasks such as detection and segmentation. We demonstrate competitive performance in comparison with training using only real images. Furthermore, bootstrapping the generated synthetic data in few-shot learning can significantly improve the overall performance, reducing the number of required training data samples to achieve the desired accuracy.

Visuo-haptic transfer for object recognition in children with periventricular leukomalacia and bilateral cerebral palsy

ABSTRACTObject recognition is a complex adaptive process that can be impaired in children with neurodevelopmental disabilities. Recently, we found a significant effect of time on the development of unimodal and crossmodal recognition skills for common objects in typical children and this was a starting point for the study of visuo-haptic object recognition skills in impaired populations. In this study, we investigated unimodal visual information, unimodal haptic information and visuo-haptic information transfer in 30 children, from 4.0 to 10.11 years of age, with bilateral Periventricular Leukomalacia (PVL) and bilateral cerebral palsy. Results were matched with those of 116 controls. Participants were tested using a clinical protocol, adopted in the previous study, involving visual exploration of black-and-white photographs of common objects, haptic exploration of real objects and visuo-haptic transfer of these two types of information. Results show that in the PVL group as in controls, there is an age-dependent development of object recognition abilities for visual, haptic and visuo-haptic modalities, even if PVL children perform worse in all the three conditions, in comparison with the typical group. Furthermore, PVL children have a specific deficit both in visual and haptic information processing, that improves with age, probably thanks to everyday experience, but the visual modality shows a better and more rapid maturation, remaining more salient compared to the haptic one. However, multisensory processes partially facilitate recognition of common objects also in PVL children and this finding could be useful for planning early intervention in children with brain lesion.

Automated analysis of visual leaf shape features for plant classification

A large number of studies have been performed during the past few years to automatically identify the plant type in a given image. Besides common object recognition difficulties arising mainly due to light, pose and orientation variations, the plant type identification problem is further complicated by the differences in leaf shape overage and changing leaf color under different weather conditions. The limited accuracy of existing approaches can be improved using an appropriate selection of representative leaf based features. This study evaluates different handcrafted visual leaf features, their extraction techniques, and classification methods. Towards this end, a new five-step algorithm is presented (comprising image pre-processing, segmentation, feature extraction, dimensionality reduction, and classification steps) for recognition of plant type through leaf images. The proposed algorithm is evaluated on a publicly available standard dataset ‘Flavia’ of 1600 leaf images and on a self-collected dataset of 625 leaf images. With the proposed algorithm, different classifiers such as k-nearest neighbor (KNN), decision tree, naïve Bayes, and multi-support vector machines (SVM) are tested. The best performing KNN, claimed for the final results, reveals that the proposed algorithm gives precision and recall values of 97.6% and 98.8% respectively when tested on ‘Flavia’ dataset. The proposed technique is also tested on our self-collected dataset, giving respectively 96.1% and 97.3% precision and recall measure results. Results confirm that our approach, when augmented with efficient segmentation techniques on raw leaf images, can be a significantly accurate plant type recognition method in practical situations. AlexNet, a Convolutional Neural Network (CNN) based approach is also compared for classification on the datasets as oppose to handcrafted feature-based approach and it is found that the later outperforms the former in robustness when the training dataset is small.

Development of visuo-haptic transfer for object recognition in typical preschool and school-aged children

ABSTRACTObject recognition is a long and complex adaptive process and its full maturation requires combination of many different sensory experiences as well as cognitive abilities to manipulate previous experiences in order to develop new percepts and subsequently to learn from the environment. It is well recognized that the transfer of visual and haptic information facilitates object recognition in adults, but less is known about development of this ability. In this study, we explored the developmental course of object recognition capacity in children using unimodal visual information, unimodal haptic information, and visuo-haptic information transfer in children from 4 years to 10 years and 11 months of age. Participants were tested through a clinical protocol, involving visual exploration of black-and-white photographs of common objects, haptic exploration of real objects, and visuo-haptic transfer of these two types of information. Results show an age-dependent development of object recognition abilities for visual, haptic, and visuo-haptic modalities. A significant effect of time on development of unimodal and crossmodal recognition skills was found. Moreover, our data suggest that multisensory processes for common object recognition are active at 4 years of age. They facilitate recognition of common objects, and, although not fully mature, are significant in adaptive behavior from the first years of age. The study of typical development of visuo-haptic processes in childhood is a starting point for future studies regarding object recognition in impaired populations.

Recognition of Objects in Simulated Irregular Phosphene Maps for an Epiretinal Prosthesis

Visual prostheses offer a possibility of restoring vision to the blind. It is necessary to determine minimum requirements for daily visual tasks. To investigate the recognition of common objects in daily life based on the simulated irregular phosphene maps, the effect of four parameters (resolution, distortion, dropout percentage, and gray scale) on object recognition was investigated. The results showed that object recognition accuracy significantly increased with an increase of resolution. Distortion and dropout percentage had significant impact on the object recognition; with the increase of distortion level and dropout percentage, the recognition decreased considerably. The accuracy decreased significantly only at gray level 2, whereas the other three gray levels showed no obvious difference. The two image processing methods (merging pixels to lower the resolution and edge extraction before lowering resolution) showed significant difference on the object recognition when there was a high degree of distortion level or dot dropout.

The roles of categorical and coordinate spatial relations in recognizing buildings

Categorical spatial information is considered more useful for recognizing objects, and coordinate spatial information for guiding actions--for example, during navigation or grasping. In contrast with this assumption, we hypothesized that buildings, unlike other categories of objects, require both categorical and coordinate spatial information in order to be recognized. This hypothesis arose from evidence that right-brain-damaged patients have deficits in both coordinate judgments and recognition of buildings and from the fact that buildings are very useful for guiding navigation in urban environments. To test this hypothesis, we assessed 210 healthy college students while they performed four different tasks that required categorical and coordinate judgments and the recognition of common objects and buildings. Our results showed that both categorical and coordinate spatial representations are necessary to recognize a building, whereas only categorical representations are necessary to recognize an object. We discuss our data in view of a recent neural framework for visuospatial processing, suggesting that recognizing buildings may specifically activate the parieto-medial-temporal pathway.

Does contrast reversal affect the recognition of common objects?

Does contrast reversal affect the recognition of common objects?

Developmental changes in visual object recognition between 18 and 24 months of age

Two experiments examined developmental changes in children's visual recognition of common objects during the period of 18 to 24 months. Experiment 1 examined children's ability to recognize common category instances that presented three different kinds of information: (1) richly detailed and prototypical instances that presented both local and global shape information, color, textural and featural information, (2) the same rich and prototypical shapes but no color, texture or surface featural information, or (3) that presented only abstract and global representations of object shape in terms of geometric volumes. Significant developmental differences were observed only for the abstract shape representations in terms of geometric volumes, the kind of shape representation that has been hypothesized to underlie mature object recognition. Further, these differences were strongly linked in individual children to the number of object names in their productive vocabulary. Experiment 2 replicated these results and showed further that the less advanced children's object recognition was based on the piecemeal use of individual features and parts, rather than overall shape. The results provide further evidence for significant and rapid developmental changes in object recognition during the same period children first learn object names. The implications of the results for theories of visual object recognition, the relation of object recognition to category learning, and underlying developmental processes are discussed.

Atypical development of face and greeble recognition in autism

Impaired face processing is a widely documented deficit in autism. Although the origin of this deficit is unclear, several groups have suggested that a lack of perceptual expertise is contributory. We investigated whether individuals with autism develop expertise in visuoperceptual processing of faces and whether any deficiency in such processing is specific to faces, or extends to other objects, too. Participants performed perceptual discrimination tasks, including a face inversion task and a classification-level task, which requires especially fine-grained discriminations, on three classes of stimuli: socially-laden faces, perceptually homogenous novel objects, greebles, and perceptually heterogeneous common objects. We found that children with autism develop typical levels of expertise for recognition of common objects. However, they evince poorer recognition for perceptually homogenous objects, including faces and, most especially, greebles. Documenting the atypical recognition abilities for greebles in children with autism has provided an important insight into the potential origin of the relatively poor face recognition skills. Our findings suggest that, throughout development, individuals with autism have a generalized deficit in visuoperceptual processing that may interfere with their ability to undertake configural processing, and that this, in turn, adversely impacts their recognition of within-class perceptually homogenous objects.

Distinct Patterns of Viewpoint-Dependent BOLD Activity during Common-Object Recognition and Mental Rotation

A fundamental but unanswered question about the human visual system concerns the way in which misoriented objects are recognized. One hypothesis maintains that representations of incoming stimuli are transformed via parietally based spatial normalization mechanisms (eg mental rotation) to match view-specific representations in long-term memory. Using fMRI, we tested this hypothesis by directly comparing patterns of brain activity evoked during classic mental rotation and misoriented object recognition involving everyday objects. BOLD activity increased systematically with stimulus rotation within the ventral visual stream during object recognition and within the dorsal visual stream during mental rotation. More specifically, viewpoint-dependent activity was significantly greater in the right superior parietal lobule during mental rotation than during object recognition. In contrast, viewpoint-dependent activity was significantly greater in the right fusiform gyrus during object recognition than during mental rotation. In addition to these differences in viewpoint-dependent activity, object recognition and mental rotation produced distinct patterns of brain activity, independent of stimulus rotation: object recognition resulted in greater overall activity within ventral stream visual areas and mental rotation resulted in greater overall activity within dorsal stream visual areas. The present results are inconsistent with the hypothesis that misoriented object recognition is mediated by structures within the parietal lobe that are known to be involved in mental rotation.

Face perception and within-category discrimination in prosopagnosia

Prosopagnosics are impaired at face recognition, but unimpaired, or relatively less impaired, at common object recognition. It has been suggested that this dissociation results simply from the greater difficulty of face recognition compared to object recognition, or from the greater need to discriminate visually similar members of a single category in face recognition compared to object recognition. We tested these hypotheses using the performance of normal subjects in an ‘old/new’ recognition paradigm to establish the true relative difficulty of face and object recognition, and required both normal subjects and a prosopagnosic subject to discriminate both faces and visually similar exemplars of nonface object categories. In two different experiments, the prosopagnosic patient performed disproportionately poorly with faces. These results disconfirm the hypotheses described above, and imply that prosopagnosia is an impairment of a specialized form of visual recognition that is necessary for face recognition and is not necessary, or less necessary, for the recognition of common objects.

Recognition of unfamiliar faces and common objects by neurologically impaired-learning disabled and normal children.

The performances of 29 normal and 29 neurologically impaired-learning disabled children (aged 7.3 to 15.3 yr.) were evaluated on unfamiliar face and common object recognition tasks. Although the normal children performed better, the relative difficulty of face and object recognition was the same for both groups.

A comparison of stereognostic recognition in normal children and severely subnormal adults.

Recently some doubt has been cast on the generality of Hermelin & O'Connor's (1961) finding that imbecile children perform better on a tactual exploration—tactual recognition task than do normals of equivalent mental age. The present investigation is in part a replication of the original study, using normal children and SSN adults matched for mental age. The same subjects are used to investigate differences in stereognostic recognition of familiar material, where verbal coding may be assumed to be involved.Both groups obtained higher recognition scores on the familiar material. The normals were superior to the SSNs on recognition of common objects, but the SSNs were superior to the normals on recognition of unfamiliar material. An attempt is made to explain this interaction by postulating relatively intact stereognostic ability in the SSN group and by examining the role of verbal coding in the retention of information from stereognostic exploration. It is also suggested that apparently dissonant evidence on the tactual recognition of shapes by normal and retarded children is not incompatible with the present findings.