Object recognition datasets and challenges: A review

Salari, Aria; Djavadifar, Abtin; Liu, Xiang Rui; Najjaran, Homayoun

doi:10.1016/j.neucom.2022.01.022

Cited by 47 publications

(12 citation statements)

References 131 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Image or object classification appoints a class label for the entire image, and object localization puts a bounding box on every object existing within an image [25]. While object detection represents a composite of object categorization and localization tasks, hence, it appoints label for every object of interest after putting a bounding box [26]. In this section, we review some of the related approaches and methods using deep learning that is utilized for object or image classification models, some of them are described briefly.…”

Section: Deep Learning Based Image Classification Modelsmentioning

confidence: 99%

An abbreviated review of deep learning-based image classification models

Abbood

Al-Turfi

Almajmaie

2023

IJEECS

View full text Add to dashboard Cite

Image classification is an extensively researched sub-fields of computer vision implemented in face recognition, self-driving, medical image segmentation, biological identification, and others. Traditional models of image classification require manual construction of feature extraction techniques and classification accuracy which are closely associated with these utilized techniques. During the rapid progress of multimedia technologies, the number of images that require classification got bigger, and this led to making image classification more complicated, hence, the manual construction of feature extraction techniques consumes more time and provides lower accuracy. In the recent decade, deep learning-based models have appeared in various applications. These models hold the merits of an effective extraction of image features, low-weight features filtering, a large capacity for processing, and higher classification speed and accuracy. Thus, lots of researchers have attempted to utilize deep learning algorithms, especially convolutional neural networks (CNNs) for image classification. Therefore, this paper concentrates on providing an abbreviated review of deep learning-based image classification models, by covering the recently utilized deep learning algorithms, comparing various related works and benchmark datasets mentioned in this paper, and summarizing the fundamental analysis and discussion.

show abstract

Section: Deep Learning Based Image Classification Modelsmentioning

confidence: 99%

An abbreviated review of deep learning-based image classification models

Abbood

Al-Turfi

Almajmaie

2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…Object recognition is used by artificial intelligence systems for machine learning through appropriate algorithms and software based on real-world data in order to improve their own performance through experience and for advanced deep learning [13][14][15], which is performed using advanced methods that often include artificial neural networks with multiple layers to facilitate the robotic system automatic identification in the future of all 3D material elements encountered.…”

Section: State Of the Artmentioning

confidence: 99%

Distance Assessment by Object Detection—For Visually Impaired Assistive Mechatronic System

et al. 2022

View full text Add to dashboard Cite

Techniques for the detection and recognition of objects have experienced continuous development over recent years, as their application and benefits are so very obvious. Whether they are involved in driving a car, environment surveillance and security, or assistive living for people with different disabilities, not to mention advanced robotic surgery, these techniques are almost indispensable. This article presents the research results of a distance assessment using object detection and recognition techniques. The first is a new technique based on low-cost photo cameras and special sign detection. The second is a classic approach based on a LIDAR sensor and an HQ photo camera. Its novelty, in this case, consists of the concept and prototype of the hardware subsystem for high-precision distance measurement, as well as fast and accurate object recognition. The experimentally obtained results are used for the motion control strategy (directional inverse kinematics) of the robotic arm (virtual prototype) component in special assistive devices designed for visually impaired persons. The advantages of the original technical solution, experimentally validated by a prototype system with modern equipment, are the precision and the short time required for the identification and recognition of objects at relatively short distances. The research results obtained, in both the real and virtual experiments, stand as a basis for the further development of the visually impaired mechatronic system prototype using additional ultrasonic sensors, stereoscopic or multiple cameras, and the implementation of machine-learning models for safety-critical tasks.

show abstract

“…Salar, et al, [19] opined in their recent study that huge dataset were required for DL experiments, which is usually an issue, the problem of surrounding data collection, annotation and algorithms design (especially for autonomous driving) were observed. The research work strives at handling occlusions, avoid duplicate counting and reducing the negative effects of background information.…”

Section: Challenges Of Deep Learning Algorithms In Object Detectionmentioning

confidence: 99%

Applications and Challenges of Deep Learning in Object Detection: A Survey

2022

JCBSC

View full text Add to dashboard Cite

Deep Learning (DL) of Artificial intelligence (AI) is a hot topic in the data science world. It's become crucial as many public and commercial businesses amass huge amounts of domain-specific data, which can provide useful information on issues like fraud detection, national intelligence, cyber security, medical informatics and marketing. Microsoft, Google, Twitter and Amazon Web Services for example, are evaluating very huge amounts of data for business analysis and decisions making, which has an impact on current and future technologies. Through the hierarchical learning process, DL algorithms extract high-level, complex abstractions as data representations. Scene interpretation, video surveillance, robots, and self-driving systems are just a few of the many applications that have prompted an extensive study in the field of computer vision in the last decade. Visual recognition systems, which include picture categorization, localization, and detection, are at the heart of all of these applications and have gathered a lot of research attention. These visual identification algorithms have achieved extraordinary performance, thanks to considerable advancements in neural networks, in particular deep learning. Object tracking and detection are one of the areas where computer vision has had a lot of success. The aim of this paper is to analyze the applications and challenges of DL algorithms for object detection in the last ten (10) years. The state-of-the-art object detection methods, including video tracking, are Applications … Yetunde Josephine OGUNS et al.

show abstract

Object recognition datasets and challenges: A review

Cited by 47 publications

References 131 publications

An abbreviated review of deep learning-based image classification models

An abbreviated review of deep learning-based image classification models

Distance Assessment by Object Detection—For Visually Impaired Assistive Mechatronic System

Applications and Challenges of Deep Learning in Object Detection: A Survey

Contact Info

Product

Resources

About