Off-line writer verification based on simple graphemes

Face detection, which is an effortless task for humans, is complex to perform on machines. The recent veer proliferation of computational resources is paving the way for frantic advancement of face detection technology. Many astutely developed algorithms have been proposed to detect faces. However, there is little attention paid in making a comprehensive survey of the available algorithms. This paper aims at providing fourfold discussions on face detection algorithms. First, we explore a wide variety of the available face detection algorithms in five steps, including history, working procedure, advantages, limitations, and use in other fields alongside face detection. Secondly, we include a comparative evaluation among different algorithms in each single method. Thirdly, we provide detailed comparisons among the algorithms epitomized to have an all-inclusive outlook. Lastly, we conclude this study with several promising research directions to pursue. Earlier survey papers on face detection algorithms are limited to just technical details and popularly used algorithms. In our study, however, we cover detailed technical explanations of face detection algorithms and various recent sub-branches of the neural network. We present detailed comparisons among the algorithms in all-inclusive and under sub-branches. We provide the strengths and limitations of these algorithms and a novel literature survey that includes their use besides face detection.

Human Face Detection Techniques: A Comprehensive Review and Future Research Directions

This paper proposes a multi-modal biometric recognition system using Face and Palm-print as biometric modalities. The main aim of this paper is to increase robustness of the recognition systems. Both modalities are combined using various biometric fusion techniques. Multi-modal biometric fusion can be implemented by using importantly two approaches i.e. Classification approach and Combination approach. Classification approach include techniques like k-Nearest Neighbors (kNN), Random Forest, etc. Confidence based approach include techniques like wavelet transformation, HOG, DCT, etc. Biometric fusion was implemented on matching score level. Experiments were conducted on faces94, faces95, faces96 and IITD Palmprint Database using various Face recognition and Palm recognition algorithms. Results of which are discussed further in the paper. The experimental results infer that biometric fusion greatly increase the robustness of a biometric recognition system.

Multi-Modal Biometric Recognition of Face and Palm-Print Using Matching Score Level Fusion

Emotional reactions are the best way to express human attitude and thermal imaging mainly used to utilize detection of temperature variations as in detecting spatial and temporal variation in the water status of grapevine. By merging the two facts this paper presents the Discrete Cosine Transform (DCT) with Local Entropy (LE) and Local Standard Deviation (LSD) features as an efficient filters for investigating human emotional state in thermal images. Two well known classifiers, K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) were combined with the earlier features and applied over a database with variant illumination, as well as occlusion by glasses and poses to generate a recognition model of facial expressions in thermal images. KNN based on DCT and LE gives the best accuracy compared with other classifier and features results.

https://beei.org/index.php/EEI/article/download/1230/993

Local Entropy and Standard Deviation for Facial Expressions Recognition in Thermal Imaging

This paper is presenting a handwriting strokes and grapheme-based offline writer identification framework. This framework works by firstly measuring the hand pressures during script writing using identical grapheme and writing strokes and then generates the pressure descriptors which are rotation as well as scale invariant. The descriptors are used to present different hand pressure distribution accuracies which are defined according to approximation-coefficients of the grapheme zone, perpendicular lines average over the handwritten script skeleton, stroke-width, and handwritten script skeleton grapheme. Discrete-Cosine Transform and Principal-Component-Analysis methods are used to evaluate the descriptors execution accuracy. The performance of the proposed method is assessed with the help of one-versus-all strategy and the k-fold validation is done with the help of Structural Support Vector Machine (S-SVM). Whereas heuristic enhancement calculation based simulated annealing is used to identify the S-SVM hyper parameters. The performance assessment of the handwriting strokes and grapheme based offline writer identification framework with single character gives the encouraging results. Also the combination of the characters enhances the accuracy as well as overall performance of personality identification up to 99.99%.

RETRACTED ARTICLE: Writer identification using graphemes

In this paper we have proposed a new combination of DCT with Nearest Neighbor Discriminant Analysis (NNDA) for face recognition. Discrete Cosine Transform (DCT) is a powerful transform to extract features from a face image. It is requisite to discriminate classes using extracted DCT features. Some low frequency DCT coefficients are selected and given as input for Discrimination analysis. We used DCT for feature extraction, low frequency DCT coefficients are selected since they carry most of the information, then NNDA is used for discrimination analysis. We applied 2-level Discrete Wavelet Transformation(DWT) only for non-match faces and smoothed those images by zeroing vertical coefficients of DWT, since those coefficients are responsible for the effect of small expressions and edges in facial images, considering this, image is reconstructed after zeroing its vertical DWT coefficients and classified once again. When experimented, we achieved 99% (at 50 features) and 98.5% (at 70 features) recognition rate on ORL and Yale databases respectively. This method is found to be robust for expressions and small pose variations of facial images.

Face Recognition Using Discrete Cosine Transform and Nearest Neighbor Discriminant Analysis

The study uses a thought-provoking exercise to encourage participants to pay closer attention to the perception of emotions spontaneously in speech. Emotion identification is becoming increasingly popular, and the demand for it is soaring. In terms of human communication, voice is the most natural and fastest. Various techniques have been created by various scholars to identify the emotional content of a speaker's speech. Emotion detection from a speaker's speech is tough because speech elements are more beneficial in distinguishing between various emotions

Emotion Extraction from Speech using Deep Learning

Nowadays, harmful speech is among the most difficult issues deal by internet. Hand-reporting comments and posts suspected of harmful speech on the internet is a frequent method of dealing with web suspects of harmful speech. This has many drawbacks. Because it necessitates the involvement of a human, this process takes a long time. Corpora of speech signals, a wide range of speech attributes, and systems for recognizing emotions are all included in this collection, which examines the most available research on speech emotion recognition. This paper presents the review of some extraordinary works done in this field. Furthermore, a short analysis is over the machine learning and deep learning algorithms. The state vector machine algorithm found to be very useful in the speech emotion recognition technique. The novel analysisand survey found to be very useful in for the upgraded researches. The paper also touched on the necessity of using a variety of classification models. If a future study is to be done on emotion recognition in general or on hazardous speech detection in particular, certain difficulties have been noted.

A Review And Analysis of Emotion Based Harmful Speech Detection Using Machine And Deep Learning And Future Direction

There has been a ton of study on the use of machine learning for speech processing applications, particularly voice recognition, over the past few decades. However, in recent years, research has concentrated on using deep learning for applications that relate to voice. In several applications, including speech, this new branch of machine learning has outperformed others, making it an extremely appealing topic for research. This paper presents a comprehensive review of the studies on deep learning for speech applications that have been carried out since 2017 when deep learning emerged as a new field of machine learning. This evaluation provides a rigorous statistical analysis that was completed by removing certain data from 184 papers published between 2017 and 2022. The findings presented in this paper shed light on the patterns of research in this field and concentrate attention on fresh research areas.

A Comprehensive Investigation into The Noise Reduction Techniques for Speech

The paper represents the state-of-the-art review of the machine learning methods for hate speech detection. This paper reviews novel applications of machine learning algorithms in hate speech. The machine learning based three algorithms i.e., Long-Short Term Memory, random forest, convolution neural network found to be most useful in hate speech detection. These algorithms are found to be most useful for twitter, Facebook, and other social platforms. This paper briefly surveys the most usable deep learning algorithms for detecting the hate speech in Arabic, English, Hindi, and other languages. The review result shows that the mentioned machine learning algorithms give an excellent results over other deep learning algorithm. Therefore, these three algorithms are widely acceptable for the evaluation of hate speech.

Surya Kant Tyagi

Papers

Face Recognition Using Discrete Cosine Transform and Nearest Neighbor Discriminant Analysis

Emotion Extraction from Speech using Deep Learning

A Review And Analysis of Emotion Based Harmful Speech Detection Using Machine And Deep Learning And Future Direction

A Comprehensive Investigation into The Noise Reduction Techniques for Speech

A Review on Emotion Based Harmful Speech Detection Using Machine Learning