Multi-feature fusion deep networks

Ma, Gang; Yang, Xi; Zhang, Bo; Shi, Zhongzhi

doi:10.1016/j.neucom.2016.08.059

Cited by 35 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It could not easily be enhanced with the help of single category features. However, feature combination of different category features was an effective method in classification problem (Barnes et al, ; Ma, Yang, Zhang, & Shi, ). Similarly, the feature combination of color, texture and SURF were utilized to train the traditional classifiers in this article.…”

Section: Resultsmentioning

confidence: 99%

Visual detection of sprouting in potatoes using ensemble‐based classifier

Ming

Shen

et al. 2018

J Food Process Engineering

View full text Add to dashboard Cite

This paper introduces novel methods for detection of sprouting in potatoes using machine vision. An ensemble‐based classifier was trained to detect sprouting considering the diversity of both feature extraction and classifiers. Two categories, namely manual feature extraction and automatic feature extraction, were utilized to enhance the diversity of feature extraction. In experiments, the proposed ensemble‐based classifier without multiple channels CNN (MC‐CNN) outperformed mainstream methods and achieved state‐of‐the‐art prediction rate of 0.916 and f‐measure of 0.905 under lower standard deviation. Furthermore, with the help of three different CNN classifiers, there was already an obvious improvement in the performance of ensemble‐based classifier with MC‐CNN. The prediction rate and f‐measure increased about 4∼5%, comparing to that without MC‐CNN. The results indicate that this approach has a better capability to combine the features for detection of sprouting in potatoes, in which the diversity of both feather extraction and classifier had been enhanced. Practical Applications Discrimination and classification of potato sprouting or not, which uses ensemble‐based classifier system with combine the best features.

show abstract

Section: Resultsmentioning

confidence: 99%

Visual detection of sprouting in potatoes using ensemble‐based classifier

Ming

Shen

et al. 2018

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…The purpose of feature extraction is to represent the original data in an alternate way by measuring certain properties or features that distinguish one input pattern from another pattern . The extracted feature should provide the characteristics of the input type to the classifier by considering the description of the relevant properties of the image into a feature space .…”

Section: Methodsmentioning

confidence: 99%

Computer‐aided diagnosis of retinal diseases using multidomain feature fusion

Keerthiveena

Esakkirajan

Selvakumar

et al. 2019

Int J Imaging Syst Tech

View full text Add to dashboard Cite

In this article, an attempt is made to combine both transform and spatial domain features to increase the accuracy, sensitivity, and specificity for the classification of retinal diseases. Papilloedema, macular edema, glaucoma, diabetic retinopathy (DR), and central retinal vein occlusion (CRVO) are the leading cause of blindness in humans. To identify these diseases in a mass screening process, it consumes intense labor and time. In this proposed work, an automated computer aided algorithm is developed to classify the normal from the abnormal (Papilledema, macular edema, glaucoma, DR, and CRVO) images. For any classification task, an increase in data size, number of classes, and dimension of the feature space affect the performance of any classifier.A single classifier is generally unable to handle the wide variability and scalability of the data in any problem. In the proposed algorithm, the feature fusion technique is employed to reduce the input data to the classifier. The features are extracted from wavelet packet transform (WPT) and intensity hue saturation (IHS). A support vector machine (SVM)-based learning algorithm is used to train the classifier using the extracted features. The proposed method yields better results than the existing classifier fusion method with an overall accuracy, sensitivity, specificity, positive prediction value (PPV), negative prediction value (NPV), and area under ROC curve (AUC) of 96.3%, 95.8%, 97.8%, 96.4%,98.1%, and 0.971 respectively. K E Y W O R D Sfeature fusion, intensity hue saturation, support vector machine, wavelet packet transform, weighted principal component analysis

show abstract

“…In addition, we could employ the ”Network in Network”(NIN) [ 38 ] in the future, to gain better nonlinear high-level features for representations of medical images, which may achieve better performance than our model. In the aspect of feature fusion strategies, we are interested in developing more methods like multifeature fusion deep networks (MFFDN) [ 39 ], based on denoising autoencoder, or metaspace fusion to combine homogeneous representations [ 40 ].…”

Section: Conclusion and Summarymentioning

confidence: 99%

Medical Image Classification Based on Deep Features Extracted by Deep Model and Statistic Feature Fusion with Multilayer Perceptron^‬

Lai

Deng

2018

Computational Intelligence and Neuroscience

140

View full text Add to dashboard Cite

Medical image classification is a key technique of Computer-Aided Diagnosis (CAD) systems. Traditional methods rely mainly on the shape, color, and/or texture features as well as their combinations, most of which are problem-specific and have shown to be complementary in medical images, which leads to a system that lacks the ability to make representations of high-level problem domain concepts and that has poor model generalization ability. Recent deep learning methods provide an effective way to construct an end-to-end model that can compute final classification labels with the raw pixels of medical images. However, due to the high resolution of the medical images and the small dataset size, deep learning models suffer from high computational costs and limitations in the model layers and channels. To solve these problems, in this paper, we propose a deep learning model that integrates Coding Network with Multilayer Perceptron (CNMP), which combines high-level features that are extracted from a deep convolutional neural network and some selected traditional features. The construction of the proposed model includes the following steps. First, we train a deep convolutional neural network as a coding network in a supervised manner, and the result is that it can code the raw pixels of medical images into feature vectors that represent high-level concepts for classification. Second, we extract a set of selected traditional features based on background knowledge of medical images. Finally, we design an efficient model that is based on neural networks to fuse the different feature groups obtained in the first and second step. We evaluate the proposed approach on two benchmark medical image datasets: HIS2828 and ISIC2017. We achieve an overall classification accuracy of 90.1% and 90.2%, respectively, which are higher than the current successful methods.

show abstract

Multi-feature fusion deep networks

Cited by 35 publications

References 19 publications

Visual detection of sprouting in potatoes using ensemble‐based classifier

Visual detection of sprouting in potatoes using ensemble‐based classifier

Computer‐aided diagnosis of retinal diseases using multidomain feature fusion

Medical Image Classification Based on Deep Features Extracted by Deep Model and Statistic Feature Fusion with Multilayer Perceptron^‬

Contact Info

Product

Resources

About

Multi-feature fusion deep networks

Cited by 35 publications

References 19 publications

Visual detection of sprouting in potatoes using ensemble‐based classifier

Visual detection of sprouting in potatoes using ensemble‐based classifier

Computer‐aided diagnosis of retinal diseases using multidomain feature fusion

Medical Image Classification Based on Deep Features Extracted by Deep Model and Statistic Feature Fusion with Multilayer Perceptron‬

Contact Info

Product

Resources

About

Medical Image Classification Based on Deep Features Extracted by Deep Model and Statistic Feature Fusion with Multilayer Perceptron^‬