Automatic Image Annotation Using Multi-object Identification

Image distance metric learning based on neighborhood sets for automatic image annotation

Automating the process of annotation of images is a crucial step towards efficient and effective management of increasingly high volume of content. A graph-based approach for automatic image annotation is proposed which models both feature similarities and semantic relations in a single graph. The proposed approach models the relationship between the images and words by an undirected graph. Semantic information is extracted from paired nodes. The quality of annotation is enhanced by introducing graph link weighting techniques. The proposed method achieves fast solution by using incremental fast random walk with restart (IFRWR) algorithm, without apparently affecting the accuracy of image annotation.

Using image classification approach for automatic image annotation is one promising method. In order to improve image annotation accuracy, recent researchers propose to use AdaBoost algorithm for the ensemble of classifiers. But in these researches, only fewer features are used. We construct multi-class classifiers for all the image low-level feature of multimedia content description interface and their potential combinations respectively, k-nearest neighbor classifier is used as the base classifier and dasiaone vs. onepsila scheme is chosen to build multi-class classifiers. A bi-coded chromosome genetic algorithm is used to select the optimal classifier subset as weak classifiers and corresponding weights, which are used for the combination of an ensemble classifier by weighted majority voting scheme. The results of experiment over 2000 classified Corel images show that the approach selects 4 of 325 multi-class classifiers as weak classifiers as well as corresponding optimized weights to generate an ensemble classifier. The ensemble classifier created by the bi-coded chromosome genetic algorithm has higher accuracy than that by AdaBoost algorithm.

Nowadays, humans tend to carry out activities during the day, both indoors and outdoors. Activities carried out outdoors cause human skin to often receive direct exposure to sunlight, which contains ultraviolet (UV) rays. Direct exposure to UV rays on the skin will harm the skin's health, which is the covering of the human body. Harmful effects on the skin usually include the skin becoming dark and dull, burns, and even causes cancer. One of the skin cancers that may appear on human skin is Actinic Keratosis (AK) cancer. AK cancer is a type of cancer that is classified as benign and can be cured with medical help. However, if this cancer is not caught early, it can become Squamous Cell Carcinoma (SCC), a type of malignant cancer. This research aims to design a system for identifying AK cancer types using color and texture feature extraction. RGB color feature extraction is obtained from image color segmentation and RGB values. The Gray Level Co-occurrence Matrix (GLCM) method is used to determine the texture of the skin cancer. Identification is carried out by a classification process using a Support Vector Machine (SVM), which can recognize the type of AK cancer. This research uses three classification methods: classification with color extraction, classification with texture extraction, and classification with color and texture extraction. Research shows that the highest level of accuracy in cancer recognition reaches 96% by combining color and texture extraction results as classification determinants. So, the system designed has succeeded in recognizing the type of AK cancer early on..

Image annotation systems aim at automatically annotating images with some predefined keywords. In this paper, we propose an automatic image annotation approach by incorporating word correlations into multi-class support vector machine (SVM). At first, each image is segmented into five fixed-size blocks or tiles and MPEG-7 visual descriptors are applied to represent color and texture features of blocks. Keywords are manually assigned to every block of training images. Then, multi-class SVM classifier is trained for semantic concepts. Word or concept correlations are computed by a co-occurrence matrix. The probability outputs from SVM and word correlations are combined to obtain the final results. The minimal-redundancy-maximum-relevance (mRMR) method is used to reduce feature dimensions. The experiments on Corel 5000 dataset demonstrate our approach is effective and efficient.

Joint multi-view representation and image annotation via optimal predictive subspace learning

In recent times, there have been increased rates at which researchers are searching for advanced ways of carrying out land-use land-cover (LULC) mapping, especially in developing countries. Four machine-learning algorithms, namely Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbour (K-NN), and Gaussian Mixture Models (GMM) were examined. This study also attempted to validate the various models using the index-based validation method. Accuracy assessment was performed by using the Kappa coefficient. The results of the LULC showed that RF classified 23% of the study area as bare land, SVM has 24% of the study area classified as bare land, K-NN also allotted 24% to bare land, while that of GMM classifier was 30%. The overall accuracy of RF, SVM, K-NN and GMM were 0.9840, 0.9780, 0.9641 and 0.9421 respectively. The Kappa Coefficient of the various classifiers were RF (0.9695), SVM (0.9580), K-NN (0.9319) and GMM (0.8916). This study showed that though all the algorithms performed relatively very well, RF performed better than the other classifiers. It suffices to state that, there is a need for further studies since other extraneous environmental variables may be underpinning these conclusions.

Due to an uneven climatic condition crops are being affected which leads to decrease in agriculture yield. It greatly affects global agricultural economy. However, the condition becomes more worse when diseases are identified in crops. Agriculture plays a vital role in every country’s economy. Thus, there is a need to identify the crop disease before it is visible on a crop so that disease can be avoided by using appropriate measures. The traditional way of identifying a crop disease is through observation by naked eyes. But as it requires large number of experts and continuous monitoring of crop it will be costly for large fields. Hence, an automatic system is required which can not only examine the crops to detect disease but also can classify the type of disease on crops. The proposed system determines disease from an input image. The input image has to go through following stages: Image Acquisition, Image pre-processing, Image segmentation, Feature Extraction, and Classification in order to determine diseased crop and accordingly provides remedy for that disease. Infected crop image is taken as input in Image Acquisition stage. In Image pre-processing stage noise is removed from the input image by applying gaussian blur filter and non-local means denoising algorithm. Also, the background of image is eliminated using Thresholding algorithm. To extract Region of Interest (ROI) i.e. infected region from input image K-means Clustering algorithm is used. Then color, texture and shape features are extracted from ROI and features are further send to the classification stage. Three different classification algorithms namely Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and Random Forest are implemented for classification out of which Support Vector Machine Algorithm is found to be best in terms of accuracy. Hence, classification is carried out by using Multivariate Support Vector Machine algorithm which detect disease present in crop accurately. In this way, the proposed system detects a disease from the given input image.

Speech applications, which operate a system by voice commands, facilitate web access for disabled and visually impaired users. Human-computer interactions, such as speaking and listening to web applications, provide options for developing a multimodal interaction tool in the accessible design of an intelligent web. Speaker identification and verification are essential functionalities for intelligent web programs with speech applications. This paper proposes an enhanced Gaussian mixture model (GMM) method by incorporating the information derived from the support vector machine (SVM), called EGMM-SVM, for web-based applications with speaker recognition. The EGMM-SVM improves the accuracy of the estimated likelihood scores between the speech frame and the GMM. In EGMM-SVM, SVM plays a crucial role in transmitting the quality information of the utterances from a test speaker, through the GMM when performing GMM likelihood calculations. The experimental results show that speaker recognition by using the developed EGMM-SVM with an accurate operation mechanism for Gaussian distribution derivations yields a higher recognition rate than does a conventional GMM without any considerations on the quality of test speech utterances.

Channel interference factor for the identification result is prevalent among the existing speaker recognition algorithms. In order to improve the accuracy of the algorithm, the paper utilizes the technique of latent factor analysis(LFA) to deal with the channel factors in the speaker's Gaussian Mixture Model(GMM). In the endpoint detection phase of speaker recognition, the algorithm introduces the GMM for speech modeling to accurately determine the beginning and ending points of the speech segment, and then establish speaker GMM. The algorithm use factor analysis technique to fit the differences between the speaker characteristics space and the channel space, and removes channel factor in speaker's GMM. And then the algorithm extracts GMM super-vectors as the input of Support Vector Machine(SVM) to obtain recognition results. Experimental results show that the combination of factor analysis and SVM can obtain better recognition rate and ensure the robustness of the recognition algorithm.

In the development of the voice conversion and the emotional speech style transformation in the text-to-speech systems, it is very important to obtain feedback information about the users’ opinion on the resulting synthetic speech quality. For this reason, the evaluations of the quality of the produced synthetic speech must often be performed for comparison. The main aim of the experiments described in this paper was to find out whether the classifier based on Gaussian mixture models (GMMs) could be applied for evaluation of male and female resynthesized speech that had been transformed from neutral to four emotional states (joy, surprise, sadness, and anger) spoken in Czech and Slovak languages. We suppose that it is possible to combine this GMM-based statistical evaluation with the classical one in the form of listening tests or it can replace them. For verification of our working hypothesis, a simple GMM emotional speech classifier with a one-level structure was realized. The next task of the performed experiment was to investigate the influence of different types and values (mean, median, standard deviation, relative maximum, etc.) of the used speech features (spectral and/or supra-segmental) on the GMM classification accuracy. The obtained GMM evaluation scores are compared with the results of the conventional listening tests based on the mean opinion scores. In addition, correctness of the GMM classification is analyzed with respect to the influence of the setting of the parameters during the GMM training—the number of mixture components and the types of speech features. The paper also describes the comparison experiment with the reference speech corpus taken from the Berlin database of emotional speech in German language as the benchmark for the evaluation of the performance of our one-level GMM classifier. The obtained results confirm practical usability of the developed GMM classifier, so we will continue in this research with the aim to increase the classification accuracy and compare it with other approaches like the support vector machines.

Logistic regression is a well known classification method in the field of statistical learning. Recently, a kernelized version of logistic regression has become very popular, because it allows non-linear probabilistic classification and shows promising results on several benchmark problems. In this paper we show that kernel logistic regression (KLR) and especially its sparse extensions (SKLR) are useful alternatives to standard Gaussian mixture models (GMMs) and support vector machines (SVMs) in Speaker recognition. While the classification results of KLR and SKLR are similar to the results of SVMs, we show that SKLR produces highly sparse models. Unlike SVMs the kernel logistic regression also provides an estimate of the conditional probability of class membership. In speaker identification experiments the SKLR methods outperform the SVM and the GMM baseline system on the POLY-COST database

This article presents an automatic image level annotation approach that takes advantage of both context and semantics presented in segmented images. The proposed approach is based on the optimization of classes’ scores using particle swarm optimization. In addition, random forest classifier and normalized cuts algorithm have been applied for automatic image classification, annotation, and clustering. For the proposed approach, each input image is segmented using the normalized cuts segmentation algorithm in order to create a descriptor for each segment. Two parameter selection models have been selected for particle swarm optimization algorithm and many voting techniques have been implemented to find the most suitable set of annotation words per image. Experimental results, using Corel5k benchmark annotated images dataset, demonstrate that applying optimization algorithms along with random forest classifier achieved noticeable increase in image annotation performance measures compared to related researches on the same dataset.

In this study, the classification of the speakers according to age and gender was discussed. Age and gender classes were first examined separately, and then by combining these classes a classification with a total of 7 classes was made. Speech signals represented by Mel-Frequency Cepstral Coefficients (MFCC) and delta parameters were converted into Gaussian Mixture Model (GMM) mean supervectors and classified with a Support Vector Machine (SVM). While the GMM mean supervectors were formed according to the Maximum-a-posteriori (MAP) adaptive GMM-Universal Background Model (UBM) configuration, the number of components was changed from 16 to 512, and the optimum number of components was decided. Gender classification accuracy of the system developed using aGender dataset was measured as 99.02% for two classes and 92.58% for three classes and age group classification accuracy was measured as 67.03% for female and 63.79% for male. In the classification of age and gender classes together in one step, an accuracy of 61.46% was obtained. In the study, a two-level approach was proposed for classifying age and gender classes together. According to this approach, the speakers were first divided into three classes as child, male and female, then males and females were classified according to their age groups and thus a 7-class classification was realized. This two-level approach was increased the accuracy of the classification in all other cases except when 32-component GMMs were used. While the highest improvement of 2.45% was achieved with 64 component GMMs, an improvement of 0.79 was achieved with 256 component GMMs.

This study provides a comparative assessment on the different techniques of classifying human activities performed while wearing inertial and magnetic sensor units on the chest, arms and legs. The gyroscope, accelerometer and the magnetometer in each unit are tri-axial. Naive Bayesian classifier, artificial neural networks (ANNs), dissimilarity-based classifier, three types of decision trees, Gaussian mixture models (GMMs) and support vector machines (SVMs) are considered. A feature set extracted from the raw sensor data using principal component analysis is used for classification. Three different cross-validation techniques are employed to validate the classifiers. A performance comparison of the classifiers is provided in terms of their correct differentiation rates, confusion matrices and computational cost. The highest correct differentiation rates are achieved with ANNs (99.2%), SVMs (99.2%) and a GMM (99.1%). GMMs may be preferable because of their lower computational requirements. Regarding the position of sensor units on the body, those worn on the legs are the most informative. Comparing the different sensor modalities indicates that if only a single sensor type is used, the highest classification rates are achieved with magnetometers, followed by accelerometers and gyroscopes. The study also provides a comparison between two commonly used open source machine learning environments (WEKA and PRTools) in terms of their functionality, manageability, classifier performance and execution times.