Object Classification using Ensemble of Local and Deep Features

Srivastava, Siddharth; Mukherjee, Prerana; Lall, Brejesh; Jaiswal, Kamlesh

doi:10.1109/icapr.2017.8593056

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evaluation was performed on the CIFAR-10 dataset, resulting in an accuracy of 91.8%. [3]' Fusion method that combines the VGG19 deep learning model for extracting features with the 'support vector machine (SVM)' for classifying images. They compared various neural models, including AlexNet, VGG16, and VGG19, for feature extraction.…”

Section: Related Workmentioning

confidence: 99%

Multilayer Perceptron’s Neural Network Based Image Spam Detection on Social Media

Himani Jain

2024

jes

View full text Add to dashboard Cite

Spam, typically unwanted material, can manifest in various forms, including images. While numerous machine learning techniques excel in detecting textual spam, they often falter when it comes to identifying image-based spam. This paper introduces a novel framework designed specifically for identifying image spams. Images are categorized into two groups: spam images, containing undesirable material, and ham images, encompassing everything else. In this paper, a novel technique based on CNN and gated recurrent unit (GRU) for image spam detection has been proposed. Our proposed methodology hinges on the utilization of diverse pre-trained deep learning models, such as InceptionV3, DenseNet121 (Densely Connected Convolutional Networks 121), ResNet50 (Residual Networks), VGG16 (Visual Geometry Group), and MobileNetV2, to effectively filter out unwanted spam images. We evaluate the performance of our approach using different Dataset. Additionally, we address the challenge of limited labeled data by leveraging transfer learning and employing data augmentation techniques. Experimental results demonstrate the efficacy of our proposed model, achieving impressive accuracy levels while maintaining computational efficiency, with testing times ranging from one to two seconds for the challenge dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Multilayer Perceptron’s Neural Network Based Image Spam Detection on Social Media

Himani Jain

2024

jes

View full text Add to dashboard Cite

show abstract

“…The experiment was implemented on MNIST and CIFAR-10 dataset and proved the best results. Srivastava et al (2017) proposed an ensemble of local and deep features for image classification. They compared various pre-trained convolutional neural networks for feature extraction.…”

Section: Challengesmentioning

confidence: 99%

Transfer learning for image classification using VGG19: Caltech-101 image data set

Bansal

Kumar

Sachdeva

et al. 2021

J Ambient Intell Human Comput

194

View full text Add to dashboard Cite

Image classification is getting more attention in the area of computer vision. During the past few years, a lot of research has been done on image classification using classical machine learning and deep learning techniques. Presently, deep learningbased techniques have given stupendous results. The performance of a classification system depends on the quality of features extracted from an image. The better is the quality of extracted features, the more the accuracy will be. Although, numerous deep learning-based methods have shown enormous performance in image classification, still due to various challenges deep learning methods are not able to extract all the important information from the image. This results in a reduction in overall classification accuracy. The goal of the present research is to improve the image classification performance by combining the deep features extracted using popular deep convolutional neural network, VGG19, and various handcrafted feature extraction methods, i.e., SIFT, SURF, ORB, and Shi-Tomasi corner detector algorithm. Further, the extracted features from these methods are classified using various machine learning classification methods, i.e., Gaussian Naïve Bayes, Decision Tree, Random Forest, and eXtreme Gradient Boosting (XGBClassifier) classifier. The experiment is carried out on a benchmark dataset Caltech-101. The experimental results indicate that Random Forest using the combined features give 93.73% accuracy and outperforms other classifiers and methods proposed by other authors. The paper concludes that a single feature extractor whether shallow or deep is not enough to achieve satisfactory results. So, a combined approach using deep learning features and traditional handcrafted features is better for image classification.

show abstract

“…Studies are merging a variety of independent individual models into a majority ensemble model for the goal of detecting tiredness 9 . Using an ensemble of both superficial and deep features, objects are detected 10,11 …”

Section: Introductionmentioning

confidence: 99%

“…9 Using an ensemble of both superficial and deep features, objects are detected. 10,11 Deep feature concatenation by ensemble learning was reported to be efficient. 10 In this research, ensemble learning for deep feature concatenations is used where individual and hybrid approaches are experimented with for classifying apple pests and diseases.…”

Section: Introductionmentioning

confidence: 99%

Using a novel convolutional neural network for plant pests detection and disease classification

et al. 2023

View full text Add to dashboard Cite

Background Early plant diseases and pests identification reduces social, economic, and environmental deficiencies entailing toxic chemical utilization on agricultural farms, thus posing a threat to global food security. Methodology An enhanced convolutional neural network (CNN) along with long short‐term memory (LSTM) using a majority voting ensemble classifier has been proposed to tackle plant pest and disease identification and classification. Within pre‐trained models, deep feature extractions have been obtained from connected layers. Deep features have been extracted and are sent to the LSTM layer to build a robust, enhanced LSTM‐CNN model for detecting plant pests and diseases. Experiments were carried out using a Turkey dataset, with 4447 apple pests and diseases categorized into 15 different classes. Results The study was evaluated in different CNNs using logistic regression (LR), LSTM, and extreme learning machine (ELM), focusing on plant disease detection problems. The ensemble majority voting classifier was used at the LSTM layer to detect and classify plant disease labels. Furthermore, an autonomous selection of the optimal LSTM layer network parameters was applied. Finally, the performance was validated based on sensitivity, F1 score, accuracy, and specificity using LSTM, ELM, and LR classifiers. Conclusion The presented model attained 99.2% accuracy compared to the cutting‐edge models on different classifiers such as LSTM, LR, and ELM, and performed better compared to transfer learning. Pre‐trained models, such as VGG19, VGG18, and AlexNet, demonstrated better accuracy when the fc6 layer was compared with other layers. © 2023 Society of Chemical Industry.

show abstract

Object Classification using Ensemble of Local and Deep Features

Cited by 7 publications

References 16 publications

Multilayer Perceptron’s Neural Network Based Image Spam Detection on Social Media

Multilayer Perceptron’s Neural Network Based Image Spam Detection on Social Media

Transfer learning for image classification using VGG19: Caltech-101 image data set

Using a novel convolutional neural network for plant pests detection and disease classification

Contact Info

Product

Resources

About