Late Fusion Techniques Research Articles

Multimodal Spatio-Temporal Framework for Real-World Affect Recognition

Deep learning models show great potential in applications involving video-based affect recognition, including human-computer interaction, robotic interfaces, stress and depression assessment, and Alzheimer's disease detection. The low complex Multimodal Diverse Spatio-Temporal Network (MDSTN) has been analysed to effectively capture spatio-temporal information from audio-visual modalities for affect recognition using the Acted Facial Expressions in the Wild (AFEW) dataset. The scarcity of data is handled by data augmented parallel feature extraction for visual network. Visual features extracted by carefully reviewing and customizing Convolutional 3D architecture over different ranges are combined to train a neural network for classification. Multi-resolution Cochleagram (MRCG) features from speech, along with spectral and prosodic audio features, are processed by a supervised classifier. The late fusion technique is explored to integrate audio and video modalities, considering their processing over different temporal spans. The MDSTN approach significantly boosts the accuracy of basic emotion recognition to 71.54% on the AFEW dataset. It demonstrates exceptional proficiency in identifying emotions such as disgust and surprise, thus exceeding current benchmarks in real-world affect recognition.

Wearable sensors based on artificial intelligence models for human activity recognition.

Human motion detection technology holds significant potential in medicine, health care, and physical exercise. This study introduces a novel approach to human activity recognition (HAR) using convolutional neural networks (CNNs) designed for individual sensor types to enhance the accuracy and address the challenge of diverse data shapes from accelerometers, gyroscopes, and barometers. Specific CNN models are constructed for each sensor type, enabling them to capture the characteristics of their respective sensors. These adapted CNNs are designed to effectively process varying data shapes and sensor-specific characteristics to accurately classify a wide range of human activities. The late-fusion technique is employed to combine predictions from various models to obtain comprehensive estimates of human activity. The proposed CNN-based approach is compared to a standard support vector machine (SVM) classifier using the one-vs-rest methodology. The late-fusion CNN model showed significantly improved performance, with validation and final test accuracies of 99.35 and 94.83% compared to the conventional SVM classifier at 87.07 and 83.10%, respectively. These findings provide strong evidence that combining multiple sensors and a barometer and utilizing an additional filter algorithm greatly improves the accuracy of identifying different human movement patterns.

Fuzzy-Based Fusion Model for β-Thalassemia Carriers Prediction Using Machine Learning Technique

The abnormality of haemoglobin in the human body is the fundamental cause of thalassemia disease. Thalassemia is considered a common genetic blood condition that has received extensive investigation in medical research globally. Likely, inherited disorders will be passed down to children from their parents. If both parents are beta Thalassemia carriers, 25% of their children will have intermediate or major beta thalassemia, which is fatal. An efficient method of beta thalassemia is prenatal screening after couples have received counselling. Identifying Thalassemia carriers involves a costly, time-consuming, and specialized test using quantifiable blood features. However, cost-effective and speedy screening methods must be developed to address this issue. The demise rate due to thalassemia development is outstandingly high around the globe. The passing rate due to thalassemia development can be reduced by following the proper procedure early; otherwise, it significantly impacts the body. A machine learning-based late fusion model proposes the detection of beta-thalassemia carriers by analyzing red blood cells. This study applied the late fusion technique to employ four machine learning algorithms. For identifying the beta-thalassemia carriers, logistics regression, Naïve Bayes, decision tree, and neural network have achieved an accuracy of 94.01%, 93.15%, 97.93%, and 98.07%, respectively, by using the features-based dataset. The late fusion-based ML model achieved an overall accuracy of 96% for detecting beta-thalassemia carriers. The proposed late fusion model performs better than previously published approaches regarding efficiency, reliability, and precision.

CMOT: A cross-modality transformer for RGB-D fusion in person re-identification with online learning capabilities

Person re-identification (reID) is a crucial aspect of intelligent surveillance systems, enabling the recognition of individuals across non-overlapping camera views. As compared to the RGB modality, RGB-D based reID has the potential to achieve robust and high performance by leveraging rich complementary features of both modalities, making it applicable in various occluded scenarios. However, current multimodal reID approaches often rely on late fusion or feature-level fusion techniques to combine multiple modalities, which limits their ability to proficiently exploit complementary visual and depth-related semantic information and capture complex interactions between unimodal features. To address these limitations, this paper introduces a cross-modality online transformer (CMOT) for RGB-D based person reID with online learning capabilities, which effectively utilizes both RGB and depth modalities for the extraction of spatio-temporal features and fuses across modalities. Our CMOT is composed of three main components: (1) a hypothesis generation module based on a person detector and tracker, (2) dual-stream feature extractors via convolutional neural networks (CNNs), (3) and a fusion transformer based on a self-attention-driven self-attentive modality refinement module (SAMR) and a cross-attention-driven cross-attentive modality interaction module (CAMI) to refine and fuse RGB-D complementary features extracted from the dual-stream, RGB and depth stream, CNNs. Additionally, we introduce a bottleneck enhancement feed-forward block to enhance the model’s representation capability within SAMR and CAMI, significantly reducing parameters and computations compared to the traditional feed-forward network. Moreover, we design the triplet loss function with distance measuring ability for incorporating online learning and finally CMOT works as a few-shot network for reID. Experimental results on three RGB-D person re-identification datasets, namely BIWI RGBD-ID, RobotPKU RGBD-ID, and TVPR2, demonstrate the effectiveness and robustness of CMOT.

PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment

Fruits significantly impact everyday living, i.e., Citrus fruits. Numerous fruits have a solid nutritious value and are packed with multivitamins and trace components. Citrus fruits are delicate and susceptible to many diseases and infections. Many researchers have suggested deep and machine learning-based fruit disease detection and classification models. This research presents a precise fruit disease identification model based on context data fusion with Faster-CNN in an edge computing environment. The goal is to develop an accurate, efficient, and trustable fruit disease detection model, a critical component of autonomous food production in a robotic edge platform. This research examines and explores four different diseases of Citrus fruits using CNN deep learning models to be adopted as edge computing solutions. Identification of citrus diseases such as cankers black spot, greening, scab, melanosis, and healthy citrus fruits are implemented using the proposed sequential model without pruning, with pruning having different sparsity levels followed by post quantization. Through the transfer learning method, this model is optimized for the assignment of fruit disease detection employing visuals from two patterns: Near-infrared (NIFR) and RGB. Early and late data fusion techniques for integrating multi-model (NIFR and RGB) facts are evaluated. The accuracy obtained from the proposed model for the canker disease is 97%, scab 95%, melanosis 99%, Greening 97%, Black spot 97% and healthy 97%. In this paper, the results of the proposed model are compared and evaluated with the sparsity levels of 50–80%, 60–90%, 70–90%, and 80–90% pruning and also obtained the results of post-quantization on each level. The results show that the model size with 60–90% pruning can be counteracted to the 47.64 of the baseline model without significant loss of accuracy. Moreover, post-quantization can reduce the 60–90% pruning from 28.16 to 8.72. In addition to enhanced precision, the above initiative is much faster to implement for new fruit diseases because it needs bounding box annotation instead of pixel-level annotation.

Identification and Classification of Informative Tweets During Disasters

bstract: Twitter serves as a popular social media platform for sharing information during disasters. However, the task of distinguishing informative tweets from the overwhelming volume of content can be daunting. In this research, we propose an innovative approach that combines Natural Language Processing (NLP), Exploratory Data Analysis (EDA), Support Vector Machine (SVM), and the Xception algorithm. Our objective is to effectively categorize disaster-related tweets based on their textual and visual content. By leveraging TensorFlow and Keras, we aim to accurately classify tweets as either disaster-related or unrelated. Additionally, we integrate the Google Translate API to facilitate the translation of text data into multiple languages. To enhance the precision of tweet label prediction, we utilize the late fusion technique to consolidate the output of our text-based model.

AATSN: Anatomy Aware Tumor Segmentation Network for PET-CT volumes and images using a lightweight fusion-attention mechanism

Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) provides metabolic information, while Computed Tomography (CT) provides the anatomical context of the tumors. Combined PET-CT segmentation helps in computer-assisted tumor diagnosis, staging, and treatment planning. Current state-of-the-art models mainly rely on early or late fusion techniques. These methods, however, rarely learn PET-CT complementary features and cannot efficiently co-relate anatomical and metabolic features. These drawbacks can be removed by intermediate fusion; however, it produces inaccurate segmentations in the case of heterogeneous textures in the modalities. Furthermore, it requires massive computation. In this work, we propose AATSN (Anatomy Aware Tumor Segmentation Network), which extracts anatomical CT features, and then intermediately fuses with PET features through a fusion-attention mechanism. Our anatomy-aware fusion-attention mechanism fuses the selective useful CT and PET features instead of fusing the full features set. Thus this not only improves the network performance but also requires lesser resources. Furthermore, our model is scalable to 2D images and 3D volumes. The proposed model is rigorously trained, tested, evaluated, and compared to the state-of-the-art through several ablation studies on the largest available datasets. We have achieved a 0.8104 dice score and 2.11 median HD95 score in a 3D setup, while 0.6756 dice score in a 2D setup. We demonstrate that AATSN achieves a significant performance gain while being lightweight at the same time compared to the state-of-the-art methods. The implications of AATSN include improved tumor delineation for diagnosis, analysis, and radiotherapy treatment.

Comparison of multimodal RGB-thermal fusion techniques for exterior wall multi-defect detection

Exterior wall inspections are critical to ensuring public safety around aging buildings in urban cities. Conventional manual approaches are dangerous, time-consuming and labor-intensive. AI-enabled drone platforms have recently become popular and provide an alternative to serving automated and intelligent inspections. However, current identification only investigates RGB image of visual defects or thermal images of thermal anomalies without considering the continuous monitoring and the conversion between multiple defects. To gain new insights with modality-specific information, this research therefore compares the performance of early, intermediate, and late multimodal RGB-Thermal images fusion techniques for multi-defect detection in facades, especially for detached tiles and missing tiles. Numerous RGB and thermals images from an ageing campus building were collected as a dataset and the classical UNet for image segmentation was modified as a benchmark. The comparative results regarding accuracy (mAP, ROC, and AUC) proved that early fusion model performed well in distinguishing detached tiles and missing tiles from complex and congested facades. Nevertheless, intermediate and late fusion models were proven to be more efficient and effective with an optimal architecture, achieving high mean average accuracy with much less parameters. In addition, the results also showed that multi-modal fusion techniques can significantly improve the performance of multi-defects detection without adding a large number of parameters to single-modal AI models.

Schizo-Net: A novel Schizophrenia Diagnosis framework using late fusion multimodal deep learning on Electroencephalogram-based Brain connectivity indices.

Schizophrenia (SCZ) is a serious mental condition that causes hallucinations, delusions, and disordered thinking. Traditionally, SCZ diagnosis involves the subject's interview by a skilled psychiatrist. The process needs time and is bound to human errors and bias. Recently, brain connectivity indices have been used in a few pattern recognition methods to discriminate neuro-psychiatric patients from healthy subjects. The study presents Schizo-Net, a novel, highly accurate, and reliable SCZ diagnosis model based on a late multimodal fusion of estimated brain connectivity indices from EEG activity. First, the raw EEG activity is pre-processed exhaustively to remove unwanted artifacts. Next, six brain connectivity indices are estimated from the windowed EEG activity, and six different deep learning architectures (with varying neurons and hidden layers) are trained. The present study is the first which considers a large number of brain connectivity indices, especially for SCZ. A detailed study was also performed that identifies SCZ-related changes occurring in brain connectivity, and the vital significance of BCI is drawn in this regard to identify the biomarkers of the disease. Schizo-Net surpasses current models and achieves 99.84% accuracy. An optimum deep learning architecture selection is also performed for improved classification. The study also establishes that Late fusion technique outperforms single architecture-based prediction in diagnosing SCZ.

Survey on Identification and Classification of Informative Tweets During Disasters

Abstract: During the time of crisis, people often post countless instructive and informative tweets on various social media platforms like Twitter. Recognizing informative tweets could be a difficult errand during the fiasco from such an enormous pool of tweets. As a solution to the current issue of sorting out enlightening tweets, we present a technique to perceive the distinguishing calamity related informative tweets from the Twitter streams utilizing the textual content. Our objective is to construct a model by using Natural Language Processing(NLP), Exploratory Data Analysis(EDA) and Support Vector Machine(SVM) and Visual Geometry Group (VGG as Deep CNN) to categorize the textual and pictorial content for the tweets. In this kernel we’ll explore classification of tweets as disaster or non- disaster, using TensorFlow and Keras. The output of the text-based model is consolidated using the late fusion technique to predict the tweet label.

TomFusioNet: A tomato crop analysis framework for mobile applications using the multi-objective optimization based late fusion of deep models and background elimination

Crop disease is a critical concern for the farmers which needs to be addressed to mitigate production loss. Multifarious frameworks have been proposed for the rapid recognition of tomato crop diseases, however, their practical deployment is a daunting task. The existing models suffer from performance issues such as overfitting and gradient vanishing. To alleviate these issues, this research proposes an end-to-end tomato crop analysis framework, TomFusioNet, for mobile applications. For feature extraction, the late-fusion technique is leveraged by aggregating the results of modified cross-domain transfer learning models using the maximum likelihood prediction strategy. Multi-layer Perceptron models are utilized as meta-learners. TomFusioNet’s pipeline comprises two modules, namely, DeepRec and DeepPred. DeepRec provides preliminary disease recognition results while DeepPred further identifies the type of illness in crop. Logic gate mapping is employed to reduce unnecessary wastage of mobile computation. The hyperparameters of DeepPred are tuned using the multi-objective optimization based non-dominated sorting genetic algorithm II for performance enhancement. We highlighted the significance of feature relevancy; therefore, a hue, saturation and value (HSV) color model-based background elimination technique is also proposed. TomFusioNet can be incorporated in a smartphone app, conceptualized for remote crop monitoring. The proposed DeepRec and DeepPred models achieved an average accuracy of 99.93% and 98.32%, respectively. According to experimental results, TomFusioNet, which is built on NSGA-II, beats state-of-the-art models with a convergence loss of 0.021 and an AUC value of 99.10%. The proposed app framework’s functioning does not require any human in loop. Furthermore, the latency of framework in real-time is less than 2 s, hence, it is effective for rapid tomato crop analysis.

ExpertosLF: dynamic late fusion of CBIR systems using online learning with relevance feedback.

One of the main challenges in CBIR systems is to choose discriminative and compact features, among dozens, to represent the images under comparison. Over the years, a great effort has been made to combine multiple features, mainly using early, late, and hierarchical fusion techniques. Unveiling the perfect combination of features is highly domain-specific and dependent on the type of image. Thus, the process of designing a CBIR system for new datasets or domains involves a huge experimentation overhead, leading to multiple fine-tuned CBIR systems. It would be desirable to dynamically find the best combination of CBIR systems without needing to go through such extensive experimentation and without requiring previous domain knowledge. In this paper, we propose ExpertosLF, a model-agnostic interpretable late fusion technique based on online learning with expert advice, which dynamically combines CBIR systems without knowing a priori which ones are the best for a given domain. At each query, ExpertosLF takes advantage of user’s feedback to determine each CBIR contribution in the ensemble for the following queries. ExpertosLF produces an interpretable ensemble that is independent of the dataset and domain. Moreover, ExpertosLF is designed to be modular, and scalable. Experiments on 13 benchmark datasets from the Biomedical, Real, and Sketch domains revealed that: (i) ExpertosLF surpasses the performance of state of the art late-fusion techniques; (ii) it successfully and quickly converges to the performance of the best CBIR sets across domains without any previous domain knowledge (in most cases, fewer than 25 queries need to receive human feedback).

A multimodal deep learning infused with artificial algae algorithm – An architecture of advanced E-health system for cancer prognosis prediction

Cancer becomes life-threatening when it affects vital organs and their potential to function; therefore, early discovery is crucial for prognosis management. Medical research benefits from the rapid growth of Artificial Intelligence (AI) technology, notably machine learning (ML), deep learning (DL), and reinforcement learning (RL) which has resulted in the development of several approaches and techniques for improving cancer prediction and survival analysis. To improve cancer prognosis prediction and survival analysis, a novel framework that fuses multimodal features via early and late fusion techniques using DL and RL is presented. The approach utilizes an artificial algae algorithm (AAA) to extract the most resilient features from the dataset and build a robust model for cancer prognosis and prediction. The uniqueness of this technique is illustrated by using AAA to extract valuable features from a variety of data modalities infused with Double DEEP Q-NETWORK (DDQN), Convolution eXtreme Gradient Boosting (CNN-XGBOOST), and Convolution Support Vector Machine (CNN-SVM) models for cancer prognostic prediction. The effectiveness of the proposed framework was evaluated using publicly-available datasets: Lower Grade Glioma in the Brain(BRAIN-TCGA), Prostate Cancer, Bladder Cancer, Metastatic Colorectal Cancer (MSKCC), and the METABRIC dataset. The optimum accuracy achieved was 0.99 for the BRAIN-TCGA dataset, surpassing a variety of state-of-the-art techniques. The performance assessment results reveal that the proposed model outperforms currently available cancer prognostic prediction models in terms of predictive performance.

Using Motion History Images With 3D Convolutional Networks in Isolated Sign Language Recognition

Sign language recognition using computational models is a challenging problem that requires simultaneous spatio-temporal modeling of the multiple sources, i.e. faces, hands, body, etc. In this paper, we propose an isolated sign language recognition model based on a model trained using Motion History Images (MHI) that are generated from RGB video frames. RGB-MHI images represent spatio-temporal summary of each sign video effectively in a single RGB image. We propose two different approaches using this RGB-MHI model. In the first approach, we use the RGB-MHI model as a motion-based spatial attention module integrated into a 3D-CNN architecture. In the second approach, we use RGB-MHI model features directly with the features of a 3D-CNN model using a late fusion technique. We perform extensive experiments on two recently released large-scale isolated sign language datasets, namely AUTSL and BosphorusSign22k. Our experiments show that our models, which use only RGB data, can compete with the state-of-the-art models in the literature that use multi-modal data.

ARCNN framework for multimodal infodemic detection

Fake news and misinformation have adopted various propagation media over time, nowadays spreading predominantly through online social networks. During the ongoing COVID-19 pandemic, false information is affecting human life in many spheres The world needs automated detection technology and efforts are being made to meet this requirement with the use of artificial intelligence. Neural network detection mechanisms are robust and durable and hence are used extensively in fake news detection. Deep learning algorithms demonstrate efficiency when they are provided with a large amount of training data. Given the scarcity of relevant fake news datasets, we built the Coronavirus Infodemic Dataset (CovID), which contains fake news posts and articles related to coronavirus. This paper presents a novel framework, the Allied Recurrent and Convolutional Neural Network (ARCNN), to detect fake news based on two different modalities: text and image. Our approach uses recurrent neural networks (RNNs) and convolutional neural networks (CNNs) and combines both streams to generate a final prediction. We present extensive research on various popular RNN and CNN models and their performance on six coronavirus-specific fake news datasets. To exhaustively analyze performance, we present experimentation performed and results obtained by combining both modalities using early fusion and four types of late fusion techniques. The proposed framework is validated by comparisons with state-of-the-art fake news detection mechanisms, and our models outperform each of them.

A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf Disease Classification

Analysis of the symptoms of rose leaves can identify up to 15 different diseases. This research aims to develop Convolutional Neural Network models for classifying the diseases on rose leaves using hybrid deep learning techniques with Support Vector Machine (SVM). The developed models were based on the VGG16 architecture and early or late fusion techniques were applied to concatenate the output from a fully connected layer. The results showed that the developed models based on early fusion performed better than the developed models on either late fusion or VGG16 alone. In addition, it was found that the models using the SVM classifier had better efficiency in classifying the diseases appearing on rose leaves than the models using the softmax function classifier. In particular, a hybrid deep learning model based on early fusion and SVM, which applied the categorical hinge loss function, yielded a validation accuracy of 88.33% and a validation loss of 0.0679, which were higher than the ones of the other models. Moreover, this model was evaluated by 10-fold cross-validation with 90.26% accuracy, 90.59% precision, 92.44% recall, and 91.50% F1-score for disease classification on rose leaves.

Acoustic-Based UAV Detection Using Late Fusion of Deep Neural Networks

Multirotor UAVs have become ubiquitous in commercial and public use. As they become more affordable and more available, the associated security risks further increase, especially in relation to airspace breaches and the danger of drone-to-aircraft collisions. Thus, robust systems must be set in place to detect and deal with hostile drones. This paper investigates the use of deep learning methods to detect UAVs using acoustic signals. Deep neural network models are trained with mel-spectrograms as inputs. In this case, Convolutional Neural Networks (CNNs) are shown to be the better performing network, compared with Recurrent Neural Networks (RNNs) and Convolutional Recurrent Neural Networks (CRNNs). Furthermore, late fusion methods have been evaluated using an ensemble of deep neural networks, where the weighted soft voting mechanism has achieved the highest average accuracy of 94.7%, which has outperformed the solo models. In future work, the developed late fusion technique could be utilized with radar and visual methods to further improve the UAV detection performance.

Automatic chronic degenerative diseases identification using enteric nervous system images.

Studies recently accomplished on the Enteric Nervous System have shown that chronic degenerative diseases affect the Enteric Glial Cells (EGC) and, thus, the development of recognition methods able to identify whether or not the EGC are affected by these type of diseases may be helpful in its diagnoses. In this work, we propose the use of pattern recognition and machine learning techniques to evaluate if a given animal EGC image was obtained from a healthy individual or one affect by a chronic degenerative disease. In the proposed approach, we have performed the classification task with handcrafted features and deep learning-based techniques, also known as non-handcrafted features. The handcrafted features were obtained from the textural content of the ECG images using texture descriptors, such as the Local Binary Pattern (LBP). Moreover, the representation learning techniques employed in the approach are based on different Convolutional Neural Network (CNN) architectures, such as AlexNet and VGG16, with and without transfer learning. The complementarity between the handcrafted and non-handcrafted features was also evaluated with late fusion techniques. The datasets of EGC images used in the experiments, which are also contributions of this paper, are composed of three different chronic degenerative diseases: Cancer, Diabetes Mellitus, and Rheumatoid Arthritis. The experimental results, supported by statistical analysis, show that the proposed approach can distinguish healthy cells from the sick ones with a recognition rate of 89.30% (Rheumatoid Arthritis), 98.45% (Cancer), and 95.13% (Diabetes Mellitus), being achieved by combining classifiers obtained on both feature scenarios.

MEMES CLASSIFICATION SYSTEM USING COMPUTER VISION AND NLP TECHNIQUES

—A meme is a culturally relevant, and brief form of media that raise a content over the internet. Now a days posting a meme is popular communication medium, due to its multimodal nature. Postings of hateful memes or fooling, cyberbullying are growing gradually. Meme takes a major part in forming people’s trust and perspective. Meme can be quickly post by anybody, and its integrity stands compromised. Hateful and aggressive matter detection have been largely traversed in a form such as text or image. And Memes complicate the task, because some meme can have a good caption and normal pictures, but if combined in some way, they can become offensive. So, it is required to fuse both modality to identify whether a given meme is hateful or not. So here for text classification we found the sequential model like Bi-LSTM and for image we will go with CNN. Late fusion technique is used to combine the image and text mode with EX-OR method to investigate its effectiveness.

Robust Person Re-Identification Through the Combination of Metric Learning and Late Fusion Techniques

Fusion techniques with the aim to leverage the discriminative power of different appearance features for person representation have been widely applied in person re-identification. They are performed by concatenating all feature vectors (known as early fusion) or by combining matching scores of different classifiers (known as late fusion). Previous studies have proved that late fusion techniques achieve better results than early fusion ones. However, majority of the studies focus on determining the suitable weighting schemes that can reflect the role of each feature. The determined weights are then integrated in conventional similarity functions, such as Cosine [L. Zheng, S. Wang, L. Tian, F. He, Z. Liu and Q. Tian, Queryadaptive late fusion for image search and person reidentification, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2015, pp. 1741–1750]. The contribution of this paper is two-fold. First, a robust person re-identification method by combining the metric learning with late fusion techniques is proposed. The metric learning method Cross-view Quadratic Discriminant Analysis (XQDA) is employed to learn a discriminant low dimensional subspace to minimize the intra-person distance while maximize the inter-person distance. Moreover, product rule-based and sum rule-based late fusion techniques are applied on these distances. Second, concerning feature engineering, the ResNet extraction process has been modified in order to extract local features of different stripes in person images. To show the effectiveness of the proposed method, both single-shot and multi-shot scenarios are considered. Three state-of-the-art features that are Gaussians of Gaussians (GOG), Local Maximal Occurrence (LOMO) and deep-learned features extracted through a Residual network (ResNet) are extracted from person images. The experimental results on three benchmark datasets that are iLIDS-VID, PRID-2011 and VIPeR show that the proposed method [Formula: see text]% [Formula: see text]% of improvement over the best results obtained with the single feature. The proposed method that achieves the accuracy of 85.73%, 93.82% and 50.85% at rank-1 for iLIDS-VID, PRID-2011 and VIPeR, respectively, outperforms different SOTA methods including deep learning ones. Source code is publicly available to facilitate the development of person re-ID system.