Deep learning vs. bag of features in machine learning for image classification

Loussaief, Sehla; Abdelkrim, Afef

doi:10.1109/aset.2018.8379825

Cited by 43 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) The Bag of Features paradigm and CNN as features extraction and image encoding methods [27,28]. Our experimentation results shown in Fig.3,4 demonstrated how CNN performs better than BoF as features extractor and image encoding technique [30].…”

Section: Problem Statementmentioning

confidence: 84%

Convolutional Neural Network Hyper-Parameters Optimization based on Genetic Algorithms

Loussaief¹,

Abdelkrim²

2018

ijacsa

Self Cite

View full text Add to dashboard Cite

In machine learning for computer vision based applications, Convolutional Neural Network (CNN) is the most widely used technique for image classification. Despite these deep neural networks efficiency, choosing their optimal architecture for a given task remains an open problem. In fact, CNNs performance depends on many hyper-parameters namely CNN depth, convolutional layer number, filters number and their respective sizes. Many CNN structures have been manually designed by researchers and then evaluated to verify their efficiency. In this paper, our contribution is to propose an innovative approach, labeled Enhanced Elite CNN Model Propagation (Enhanced E-CNN-MP), to automatically learn the optimal structure of a CNN. To traverse the large search space of candidate solutions our approach is based on Genetic Algorithms (GA). These meta-heuristic algorithms are wellknown for non-deterministic problem resolution. Simulations demonstrate the ability of the designed approach to compute optimal CNN hyper-parameters in a given classification task. Classification accuracy of the designed CNN based on Enhanced E-CNN-MP method, exceed that of public CNN even with the use of the Transfer Learning technique. Our contribution advances the current state by offering to scientists, regardless of their field of research, the ability of designing optimal CNNs for any particular classification problem.

show abstract

Section: Problem Statementmentioning

confidence: 84%

Convolutional Neural Network Hyper-Parameters Optimization based on Genetic Algorithms

Loussaief¹,

Abdelkrim²

2018

ijacsa

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the literature, BoF paradigm has been largely used for handcrafted feature quantization [11,12] to accomplish image classi cation tasks. A comparative study between BoF and deep learning for image classi cation has been made in Loussaief and Abdelkrim [13]. To take the advantages of the two techniques, BoF is considered, in this paper, as a pooling layer in our trainable convolutional layers which aims to reduce the number of parameters and makes possible to classify masked face images.…”

Section: Motivation and Contribution Of The Papermentioning

confidence: 99%

Efficient Masked Face Recognition Method during the COVID-19 Pandemic

Hariri

2020

Preprint

View full text Add to dashboard Cite

Abstract The COVID-19 is an unparalleled crisis leading to huge number of casualties and security problems. In order to reduce the spread of coronavirus, people often wear masks to protect themselves. This makes the face recognition a very difficult task since certain parts of the face are hidden. A primary focus of researchers during the ongoing coronavirus pandemic is to come up with suggestions to handle this problem through rapid and efficient solutions. In this paper, we propose a reliable method based on discard masked region and deep learning based features in order to address the problem of masked face recognition process. The first step is to discard the masked face region. Next, we apply a pre-trained deep Convolutional neural networks (CNN) to extract the best features from the obtained regions (mostly eyes and forehead regions). Finally, the Bag-of-features paradigm is applied on the feature maps of the last convolutional layer in order to quantize them and to get a slight representation comparing to the fully connected layer of classical CNN. Finally, MLP is applied for the classification process. Experimental results on Real-World-Masked-Face-Dataset show high recognition performance.

show abstract

“…Traditional feature-based and descriptor-based techniques, such as Bag of Features (BoF) (O'Hara and Draper, 2011), shape descriptors for object retrieval (López et al, 2017), Local Binary Pattern (LBP) (Fronitasari and Gunawan, 2017), and Speeded-Up Robust Features (SURF) (Srivastava et al, 2019), rely on different sets of features designed to extract meaningful characteristics of regions in an image, which allows the detection and classification of objects. In practice, these approaches involve a high degree of parameter tuning, limiting their scalability and adaptability to new scenarios, such as different lighting conditions or camera angles (Loussaief and Abdelkrim, 2018).…”

Section: Vision-based Object Identificationmentioning

confidence: 99%

FAIM: Vision and Weight Sensing Fusion Framework for Autonomous Inventory Monitoring in Convenience Stores

Falcão

Ruiz²,

Pan

et al. 2020

Front. Built Environ.

View full text Add to dashboard Cite

A common pain point for physical retail stores is live inventory monitoring, i.e., knowing how many items of each product are left on the shelves. About 4% of sales are lost due to an average 5-10% out-of-shelf stockout rate, while additional supplies existed in the warehouse. Traditional techniques rely on manual inspection, per-item tagging using RFIDs, or human-in-the-loop systems, such as Amazon Go. These approaches, while effective, either have poor accuracy, long delays between results or are cost prohibitive. In this paper, we present FAIM (Autonomous Inventory Monitoring Framework) for cashier-less stores. To the best of our knowledge, this is the first fully autonomous system that fuses multiple sensing modalities. Utilizing weight difference on a shelf, visual item recognition in customers' hands and prior knowledge of item layout FAIM monitors products picked up or returned without human-in-the-loop. We present results from a real-world setup with 85 items (33 unique products) replicating the layout of a local 7-Eleven store. To evaluate our system we characterize the similarity of the unique products across three physical features (i.e., weight, color, and location). Our results show that the fused approach provides up to 92.6% item identification accuracy, a 2× reduction in error compared to reported self-checkout stations.

show abstract

Deep learning vs. bag of features in machine learning for image classification

Cited by 43 publications

References 10 publications

Convolutional Neural Network Hyper-Parameters Optimization based on Genetic Algorithms

Convolutional Neural Network Hyper-Parameters Optimization based on Genetic Algorithms

Efficient Masked Face Recognition Method during the COVID-19 Pandemic

FAIM: Vision and Weight Sensing Fusion Framework for Autonomous Inventory Monitoring in Convenience Stores

Contact Info

Product

Resources

About