Deep Appearance Model and Crow-Sine Cosine Algorithm-Based Deep Belief Network for Age Estimation
01 Jul 2021-International Journal of Ambient Computing and Intelligence (IGI Global)-Vol. 12, Iss: 3, pp 185-207
TL;DR: The overall process of age estimation is performed using three important steps, where the DBN classifier is trained optimally using the proposed learning algorithm named as crow-sine cosine algorithm (CS).
Abstract: Age estimation has been paid great attention in the field of intelligent surveillance, face recognition, biometrics, etc. In contrast to other facial variations, aging variation presents several unique characteristics, which make age estimation very challenging. The overall process of age estimation is performed using three important steps. In the first step, the pre-processing is performed from the input image based on Viola-Jones algorithm to detect the face region. In the second step, feature extraction is done based on three important features such as local transform directional pattern (LTDP), active appearance model (AAM), and the new feature, deep appearance model (Deep AM). After feature extraction, the classification is carried out based on the extracted features using deep belief network (DBN), where the DBN classifier is trained optimally using the proposed learning algorithm named as crow-sine cosine algorithm (CS).
Citations
More filters
TL;DR: In this paper , an effective cloud IDS using Grasshopper optimization algorithm (GOA) and deep belief network (DBN) is proposed to solve the issues and to increase the accuracy.
Abstract: Cloud computing is a vast area which uses the resources cost-effectively. The performance aspects and security are the main issues in cloud computing. Besides, the selection of optimal features and high false alarm rate to maintain the highest accuracy of the testing are also the foremost challenges focused. To solve these issues and to increase the accuracy, an effective cloud IDS using Grasshopper optimization Algorithm (GOA) and Deep belief network (DBN) is proposed in this paper. GOA is used to choose the ideal features from the set of features. Finally, DBN is developed for classification according to their selected feasible features. The introduced IDS is simulated on the Python platform and the performance of the suggested model of deep learning is assessed based on statistical measures named as Precision, detection accuracy, f-measure and Recall. The NSL_KDD, and UNSW_NB15 are the two datasets used for the simulation, and the results showed that the proposed scheme achieved maximum classification accuracy and detection rate.
2 citations
TL;DR: In this paper , Pseudo Zernike Moments (PZM), Active Appearance Model (AAM), Bio-Inspired Features (BIF), Support Vector Machine (SVM) and Support Vector Regression (SVR) algorithms are used to predict the age range of face images.
Abstract: Abstract Age estimation from face images is one of the significant topics in the field of machine vision, which is of great interest to controlling age access and targeted marketing. In this article, there are two main stages for human age estimation; the first stage consists of extracting features from the face areas by using Pseudo Zernike Moments (PZM), Active Appearance Model (AAM), and Bio-Inspired Features (BIF). In the second step, Support Vector Machine (SVM) and Support Vector Regression (SVR) algorithms are used to predict the age range of face images. The proposed method has been assessed utilizing the renowned databases of IMDB-WIKI and WIT-DB. In general, from all results obtained in the experiments, we have concluded that the proposed method can be chosen as the best method for Age estimation from face images.
References
More filters
TL;DR: The main aspects that can increase the performance of the age estimation system are analyzed, the handcrafted- based models and deep learning-based models are presented, and how the evaluations are being conducted are shown.
Abstract: Recently, vast attention has grown in the field of computer vision, especially in face recognition, detection, and facial landmarks localization. Many significant features can be directly derived from the human face, such as age, gender, and race. Estimating the age can be defined as the automatic process of classifying the facial image into the exact age or to a specific age range. Practically, age estimation from the face is still a challenging problem due to the effects from many internal factors, such as gender and race, and external factors, such as environments and lifestyle. Huge efforts have been addressed to reach an accepted and satisfied accuracy of age estimation task. In this paper, we try to analyze the main aspects that can increase the performance of the age estimation system, present the handcrafted-based models and deep learning-based models, and show how the evaluations are being conducted, discuss the proposed algorithms and models in the age estimation, and show the main limitations and challenges facing the age estimation process. Also, different aging databases that contain age annotations are discussed. Finally, few guidelines and the future prospect related to the age estimation are investigated.
23 citations
TL;DR: This paper presents a novel hierarchical Gaussian process framework for automatic age estimation that consists of multi-classGaussian process classifier to classify the input images into different age groups followed by a warped Gaussian process regression to model group specific aging patterns.
Abstract: Automatic age estimation from facial images has attracted increasing attention due to its promising potential in real-life computer vision applications. However, due to uncontrollable environments, insufficient and incomplete training data, strong person-specific and large within- age span variations, age estimation has become a challenging problem. Among published age estimation, hierarchical age estimation methods have achieved comparable performance improvement than single level approaches. Most of the published hierarchical approaches have mainly used support vector machines to classify age groups followed by support vector regression for withina- age group age estimation. In this paper, we present a novel hierarchical Gaussian process framework for automatic age estimation. It consists of multi-class Gaussian process classifier to classify the input images into different age groups followed by a warped Gaussian process regression to model group specific aging patterns. In this paper, we separately tune the hyper-parameters for each age group at the regression stage. Compared with existing single level Gaussian process approaches for age estimation, our approach is computationally efficient at both the levels of hierarchy. Partitioning data into different age groups and learning group-wise hyper-parameters is computationally more efficient than learning complete training data. Misclassifications at the group boundaries are compensated at the regression stage by overlapping the neighboring age ranges. Finally, through extensive experiments on two popular aging datasets, the FG-NET and the Morph-II, we demonstrate the effectiveness of our algorithm in improving age estimation performance.
21 citations
01 Feb 2019
TL;DR: The paper shows that transfer learning allows the use of pre-trained DCNNs regardless of the type of ages (apparent or biological) that is adopted in DCNN training.
Abstract: This paper was aimed to address the problem of image-based human age estimation It has the following main contributions First, we provide a comparison of three hand-crafted image features and five deep convolutional neural networks (DCNNs) Secondly, we show that the use of pre-trained DCNNs as feature extractors can transfer the knowledge of DCNNs to new datasets and domains that were not necessarily addressed in the training phase This is achieved by only retraining a shallow regressor over the deep features Thirdly, we provide a cross-database evaluation involving biological and apparent ages The paper shows that transfer learning allows the use of pre-trained DCNNs regardless of the type of ages (apparent or biological) that is adopted in DCNN training The experiments are carried out on three public databases: MORPH, PAL, and Chalearn2016
21 citations
TL;DR: The experimentation for anomaly detection proves that the proposed TTD and TTD-GMM method attains a higher rate of multiple object tracking precision, accuracy, and specificity at 0.975, 1, and 1, respectively.
Abstract: The anomaly detection and localisation (ADL) gains remarkable interest as dealing with the complex surveillance videos for detecting the abnormal behaviour is tedious. The human effort in monitoring and classifying the abnormal object is inaccurate and time-consuming; therefore, the method is proposed using the Tucker tensor decomposition (TTD) and classification of the objects using Gaussian mixture model (GMM). Initially, the object is detected in the frames for easy recognition using simple background subtraction. The TTD decomposes the tensor as core tensor and factor matrices and the two decomposed tensors are compared using the cosine similarity measure that determines the location of the object in the frame. Finally, the features including shape and speed of the object are extracted that is used for classification using the GMM that follows the maximum posterior probability principle to detect and locate the anomaly in the video. The experimentation for anomaly detection proves that the proposed TTD and TTD-GMM method attains a higher rate of multiple object tracking precision, accuracy, sensitivity, and specificity at 0.96375, 0.975, 1, and 1, respectively.
18 citations
TL;DR: This work extends the previous work by developing a novel path equalization scheme for equalizing the path length of the query and the tracked object, and achieving high values for precision, recall, F-measure, and multiple object tracking precision.
Abstract: Video retrieval is one of the emerging areas in video capturing that gained various technical advances, increasing the availability of a huge mass of videos. For the text or the image query given, retrieving the relevant videos and the objects from the videos is not always an easy task. A hybrid model was developed in the previous work using the Nearest Search Algorithm (NSA) and exponential weighted moving average (EWMA), for the video object retrieval. In NSA + EWMA, the object trajectories are retrieved based on the query specific distance. This work extends the previous work by developing a novel path equalization scheme for equalizing the path length of the query and the tracked object. Initially, a hybrid model based on Support Vector Regression and NSA tracks the position of the object in the video. The proposed density measure scheme equalizes the path length of the query and the object. Then, the identified path length related to the query is given to extended nearest neighbor classifier for retrieving the video. From the simulation results, it is evident that the proposed video retrieval scheme achieved high values of 0.901, 0.860, 0.849, and 0.922 for precision, recall, F-measure, and multiple object tracking precision, respectively.
16 citations