An ensemble feature method for food classification

In the last years, several works on automatic image-based food recognition have been proposed, often based on texture feature extraction and classification. However, there is still a lack of proper comparisons to evaluate which approaches are better suited for this specific task. In this work, we adopt a Random Forest classifier to measure the performances of different texture filter banks and feature encoding techniques on three different food image datasets. Comparative results are given to show the performance of each considered approach, as well as to compare the proposed Random Forest classifiers with other feature-based state-of-the-art solutions.

Download Full-text

Indonesian Traditional Food Image Identification using Random Forest Classifier based on Color and Texture Features

2019 International Conference on Sustainable Information Engineering and Technology (SIET) ◽

10.1109/siet48054.2019.8986058 ◽

2019 ◽

Author(s):

Yuita Arum Sari ◽

Fitri Utaminingrum ◽

Sigit Adinugroho ◽

Ratih Kartika Dewi ◽

Putra Pandu Adikara ◽

...

Keyword(s):

Random Forest ◽

Texture Features ◽

Random Forest Classifier ◽

Traditional Food ◽

Image Identification ◽

Food Image ◽

Color And Texture Features

Download Full-text

A Random Forest and Current Fault Texture Feature–Based Method for Current Sensor Fault Diagnosis in Three-Phase PWM VSR

Frontiers in Energy Research ◽

10.3389/fenrg.2021.708456 ◽

2021 ◽

Vol 9 ◽

Author(s):

Lei Kou ◽

Xiao-dong Gong ◽

Yi Zheng ◽

Xiu-hui Ni ◽

Yang Li ◽

...

Keyword(s):

Fault Diagnosis ◽

Random Forest ◽

Texture Feature ◽

Texture Features ◽

Current Sensor ◽

Stable Operation ◽

Sensor Faults ◽

Sensor Fault ◽

Three Phase ◽

Feature Based

Three-phase PWM voltage-source rectifier (VSR) systems have been widely used in various energy conversion systems, where current sensors are the key component for state monitoring and system control. The current sensor faults may bring hidden danger or damage to the whole system; therefore, this paper proposed a random forest (RF) and current fault texture feature–based method for current sensor fault diagnosis in three-phase PWM VSR systems. First, the three-phase alternating currents (ACs) of the three-phase PWM VSR are collected to extract the current fault texture features, and no additional hardware sensors are needed to avoid causing additional unstable factors. Then, the current fault texture features are adopted to train the random forest current sensor fault detection and diagnosis (CSFDD) classifier, which is a data-driven CSFDD classifier. Finally, the effectiveness of the proposed method is verified by simulation experiments. The result shows that the current sensor faults can be detected and located successfully and that it can effectively provide fault locations for maintenance personnel to keep the stable operation of the whole system.

Download Full-text

Extended Mapping Local Binary Pattern Operator for Texture Classification

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001417500197 ◽

2017 ◽

Vol 31 (06) ◽

pp. 1750019 ◽

Cited By ~ 6

Author(s):

Mohammad Hossein Shakoor ◽

Reza Boostani

Keyword(s):

Local Binary Pattern ◽

Accurate Result ◽

State Of The Art ◽

Texture Classification ◽

Texture Feature ◽

Mapping Technique ◽

Texture Feature Extraction ◽

Rotation Invariant ◽

Classification Rate ◽

Extended Mapping

In this paper, an Extended Mapping Local Binary Pattern (EMLBP) method is proposed that is used for texture feature extraction. In this method, by extending nonuniform patterns a new mapping technique is suggested that extracts more discriminative features from textures. This new mapping is tested for some LBP operators such as CLBP, LBP, and LTP to improve the classification rate of them. The proposed approach is used for coding nonuniform patterns into more than one feature. The proposed method is rotation invariant and has all the positive points of previous approaches. By concatenating and joining two or more histograms significant improvement can be made for rotation invariant texture classification. The implementation of proposed mapping on Outex, UIUC and CUReT datasets shows that proposed method can improve the rate of classifications. Furthermore, the introduced mapping can increase the performance of any rotation invariant LBP, especially for large neighborhood. The most accurate result of the proposed technique has been obtained for CLBP. It is higher than that of some state-of-the-art LBP versions such as multiresolution CLBP and CLBC, DLBP, VZ_MR8, VZ_Joint, LTP, and LBPV.

Download Full-text

ResNet Based Deep Features and Random Forest Classifier for Diabetic Retinopathy Detection

Sensors ◽

10.3390/s21113883 ◽

2021 ◽

Vol 21 (11) ◽

pp. 3883

Author(s):

Muhammad Kashif Yaqoob ◽

Syed Farooq Ali ◽

Muhammad Bilal ◽

Muhammad Shehzad Hanif ◽

Ubaid M. Al-Saggaf

Keyword(s):

Diabetic Retinopathy ◽

Deep Learning ◽

Random Forest ◽

Macular Edema ◽

Diabetic Macular Edema ◽

State Of The Art ◽

Random Forest Classifier ◽

Eye Disease ◽

Diabetic Patients ◽

The Right

Diabetic retinopathy, an eye disease commonly afflicting diabetic patients, can result in loss of vision if prompt detection and treatment are not done in the early stages. Once the symptoms are identified, the severity level of the disease needs to be classified for prescribing the right medicine. This study proposes a deep learning-based approach, for the classification and grading of diabetic retinopathy images. The proposed approach uses the feature map of ResNet-50 and passes it to Random Forest for classification. The proposed approach is compared with five state-of-the-art approaches using two category Messidor-2 and five category EyePACS datasets. These two categories on the Messidor-2 dataset include ’No Referable Diabetic Macular Edema Grade (DME)’ and ’Referable DME’ while five categories consist of ‘Proliferative diabetic retinopathy’, ‘Severe’, ‘Moderate’, ‘Mild’, and ‘No diabetic retinopathy’. The results show that the proposed approach outperforms compared approaches and achieves an accuracy of 96% and 75.09% for these datasets, respectively. The proposed approach outperforms six existing state-of-the-art architectures, namely ResNet-50, VGG-19, Inception-v3, MobileNet, Xception, and VGG16.

Download Full-text

Feature Descriptor for Crowd Density Estimation

10.20944/preprints201905.0198.v1 ◽

2019 ◽

Author(s):

Muhammad Bilal ◽

Adwan Alanazi

Keyword(s):

Density Estimation ◽

State Of The Art ◽

Texture Feature ◽

Support Vector ◽

Svm Classifier ◽

Feature Descriptor ◽

Crowd Density Estimation ◽

Crowd Density ◽

Feature Based ◽

Crowd Monitoring

Crowd density estimation is an important task for crowd monitoring. Many efforts have been done to automate the process of estimating crowd density from images and videos. Despite series of efforts, it remains a challenging task. In this paper, we proposes a new texture feature-based approach for the estimation of crowd density based on Completed Local Binary Pattern (CLBP). We first divide the image into blocks and then re-divide the blocks into cells. For each cell, we compute CLBP and then concatenate them to describe the texture of the corresponding block. We then train a multi-class Support Vector Machine (SVM) classifier, which classifies each block of image into one of four categories, i.e. Very Low, Low, Medium, and High. We evaluate our technique on the PETS 2009 dataset, and from the experiments, we show to achieve 95% accuracy for the proposed descriptor.  We also compare other state-of-the-art texture descriptors and from the experimental results, we show that our proposed method outperforms other state-of-the-art methods.

Download Full-text