Pseudo Zernike Research Articles

Bayesian calibration of quasi-static field distortions in HARMONI

ABSTRACT The high angular resolution monolithic optical and near-infrared Integral field spectrograph is the first light visible and near-infrared integral field spectrograph for the Extremely Large Telescope. To reach the diffraction limit of the telescope (≈ 10 mas) and maintain an optimal image quality over long exposures, an accurate measurement of geometrical distortions in the instrument’s guide star field is needed. Geometrical distortions affecting the guide stars map directly to pointing errors of the science field. The systematic contribution to the pointing error can be calibrated and removed by a corrective model. In this work, we propose a formulation of the corrective model that aims to calibrate the geometrical field distortions down to a given target residual, as well as reducing the time spent in calibrations. We also propose a calibration procedure that accounts for the uncertainties of the measurement process. We developed a tool named harmoni-pm to simulate the expected pointing error caused by geometrical distortions and validate the effectiveness of the proposed corrective model. We also relied on pseudo Zernike polynomials to formulate the model, and the Bayesian theoretical framework to study the propagation of uncertainties along the calibration process. Compared with the classical calibration algorithm, the Bayesian calibration algorithm was able to reduce the number of calibration points required to reach the same model residual. Additionally, we were able to optimize the hardware of the Geometrical Calibration Unit and reduce the time required to achieve the calibration goal.

A New Hybrid Model to Predict Human Age Estimation from Face Images Based on Supervised Machine Learning Algorithms

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.

A robust semi-fragile watermarking system using Pseudo-Zernike moments and dual tree complex wavelet transform for social media content authentication.

With the growing use of mobile devices and Online Social Networks (OSNs), sharing digital content, especially digital images is extremely high as well as popular. This made us convenient to handle the ongoing COVID-19 crisis which has brought about years of change in the sharing of digital content online. On the other hand, the digital image processing tools which are powerful enough to make the perfect image duplication compromises the privacy of the transmitted digital content. Therefore, content authentication, proof of ownership, and integrity of digital images are considered crucial problems in the world of digital that can be accomplished by employing a digital watermarking technique. On contrary, watermarking issues are to triumph trade-offs among imperceptibility, robustness, and payload. However, most existing systems are unable to handle the problem of tamper detection and recovery in case of intentional and unintentional attacks concerning these trade-offs. Also, the existing system fails to withstand the geometrical attacks. To resolve the above shortcomings, this proposed work offers a new multi-biometric based semi-fragile watermarking system using Dual-Tree Complex Wavelet Transform (DTCWT) and pseudo-Zernike moments (PZM) for content authentication of social media data. In this research work, the DTCWT-based coefficients are used for achieving maximum embedding capacity. The Rotation and noise invariance properties of Pseudo Zernike moments make the system attain the highest level of robustness when compared to conventional watermarking systems. To achieve authentication and proof of identity, the watermarks of about four numbers are used for embedding as a replacement for a single watermark image in traditional systems. Among four watermarks, three are the biometric images namely Logo or unique image of the user, fingerprint biometric of the owner, and the metadata of the original media to be transmitted. In addition, to achieve the tamper localization property, the Pseudo Zernike moments of the original cover image are obtained as a feature vector and also embedded as a watermark. To attain a better level of security, each watermark is converted into Zernike moments, Arnold scrambled image, and SHA outputs respectively. Then, to sustain the trade-off among the watermarking parameters, the optimal embedding location is determined. Moreover, the watermarked image is also signed by the owner's other biometric namely digital signature, and converted into Public key matrix Pkm and embedded onto the higher frequency subband namely, HL of the 1-level DWT. The proposed system also accomplishes a multi-level authentication, among that the first level is attained by the decryption of the extracted multiple watermark images with the help of the appropriate decryption mechanism which is followed by the comparison of the authentication key which is extracted using the key which is regenerated at the receiver's end. The simulation outcomes evident that the proposed system shows superior performance towards content authentication, to most remarkable intentional and unintentional attacks among the existing watermarking systems.

Reading signboards for the visually impaired using Pseudo-Zernike Moments

It is necessary to provide essential daily support for the visually impaired, allowing them to locate themselves in an underground station, to change trains, to read signboards like those in doctors offices, law firms, shops, etc. In this paper, we present a Reading Signboards System (called RSbS) based on Pseudo Zernike Moments (PZMs) and stroke features from a video captured by a camera. The system is made up of three main steps: (i) signboard detection, (ii) text localization and (iii) filtering of non-textual regions. In a video, signboard region contains all the necessary information. Therefore, the signboard region should be located and segmented from the other parts of a frame that will be considered as the background. Signboards localization and segmentation are performed using Pseudo Zernike Moments. Text localization and extraction is done using PZMs segmentation which is based on the HSV color space and specifically on the Value channel. Non-textual regions will be filtered out using the outline function. System evaluation shows that it is robust to changes in lighting, low resolution and camera tilt, and it gives very few false positives compared to other approaches. In addition, the resulting images are transmitted to an optical character recognition engine (the best known is OCR) to extract the text which will be converted to speech using one of the existing APIs like Google Text to Speech API (gTTS API).

Facial expression recognition using fuzzified Pseudo Zernike Moments and structural features

Facial expression recognition (FER) is an important part of emotional computing that can be useful in many applications for people's behavior analysis. Recently, some methods have been suggested to recognize facial expressions, but they do not offer a strong approach to facial expression recognition. In this paper, we propose a fuzzy-based approach that incorporates two different types of features to increase the recognition rate of facial expression. These features include locally weighted Pseudo Zernike Moments (LWPZM) and structural features (mouth and eye-opening, teeth existence, and eyebrow constriction). To classify facial expressions, the proposed fuzzy inference system uses fuzzified features. The performance of our proposed method has been assessed using the well-known RaFD database. The experimental results show that the proposed method is not only robust in terms of age, ethnicity, and gender changes that would make our contribution, but also improve the recognition rate of facial expression compared to several state-of-the-art methods.

Audio-visual speech recognition based on machine learning approach

Audio-visual speech recognition by machine plays an important role when research in automatic speech recognition reaches its highest performance. Audio alone also gives good performance, but adding the visual information potentially gives more convenient recognition system when an audio signal degrades in a noisy environment and may vary because of the environmental channel. This paper proposes an audio-visual automatic speech recognition (AV-ASR) system based on machine learning approaches. Visual information is captured from lip contour. Pseudo Zernike moments (PZMs) and 19th order Mel frequency cepstral coefficients (MFCCs) are extracted to obtain visual information and audio feature respectively. Machine learning approach, artificial neural networks (ANN) and support vector machines (SVM) are used to recognise speech for audio and visual modality. After the individual recognition of two systems, a combined decision is taken. This paper also evaluates the individual performance of both audio and visual speech recognition by machine learning approach.

Secondary Pulmonary Tuberculosis Identification Via pseudo-Zernike Moment and Deep Stacked Sparse Autoencoder.

Secondary pulmonary tuberculosis (SPT) is one of the top ten causes of death from a single infectious agent. To recognize SPT more accurately, this paper proposes a novel artificial intelligence model, which uses Pseudo Zernike moment (PZM) as the feature extractor and deep stacked sparse autoencoder (DSSAE) as the classifier. In addition, 18-way data augmentation is employed to avoid overfitting. This model is abbreviated as PZM-DSSAE. The ten runs of 10-fold cross-validation show this model achieves a sensitivity of 93.33% ± 1.47%, a specificity of 93.13% ± 0.95%, a precision of 93.15% ± 0.89%, an accuracy of 93.23% ± 0.81%, and an F1 score of 93.23% ± 0.83%. The area-under-curve reaches 0.9739. This PZM-DSSAE is superior to 5 state-of-the-art approaches.

A Novel Hybrid Feature Framework for Multi-View Age Estimation

ABSTRACT Facial age estimation has grasped the attention of numerous researchers in recent times. It is a challenging task as a consequence of illumination, pose variations, occlusion, complex background, facial expression, and facial makeup. Estimating the age of an individual with an arbitrary pose is quite a challenging job because most of the age estimation system focuses on the frontal view. In this paper, a novel framework for multi-view age estimation by amalgamating the local and global features is proposed. A novel texture feature, Median Gradient Ternary Pattern is proposed in this paper. The Pseudo Zernike Moment extracts the shape features and the View-based Active Appearance Model constructs an appearance model from the facial images. Further, all three features are combined into a feature vector by executing feature-level fusion. The dimension of the combined feature is reduced using Principal Component Analysis. Multi-class Support Vector Machine is utilized to divide the images into four poses. For each pose, a Support Vector Regression with RBF kernel is applied to train a model for estimating the actual age of an individual. The proposed methodology is performed on two databases, namely, FG-NET and CACD which showcase eminent performance.

Multi-Type Classification Comparison of Mammogram Abnormalities

Cancer is a life-threatening disease which reduces the lifespan of humans. If the disease is treated early, the lifespan can be extended. This paper provides a useful method for detecting the abnormalities in the mammograms. The proposed method uses four phases such as pre-processing, segmentation, feature extraction and classification. In the pre-processing phase, median filter is utilized to enhance the quality of an image. The pre-processed image is then segmented by fuzzy C means (FCM). Three different features such as Gaussian–Hermite moments (GHM), Jacobi moments and pseudo Zernike moments (PZM) are extracted from the segmented image. Finally, extreme learning machine (ELM) classifier identifies the normal, malignant and benign kinds of cancer. This method is compared with four different classifiers. The proposed method is tested on mammographic image analysis society (MIAS) dataset and the performance is evaluated against several analogous approaches in terms of accuracy, sensitivity and specificity. The proposed approach substantially provides the best result.

Multi-mass breast cancer classification based on hybrid descriptors and memetic meta-heuristic learning

Among the causes of death in the world, breast cancer is considered the most common cause of mortality among women to the extent that one in five deaths among women is attributed to the incidence of this cancer. In this paper, we introduce a computer-aided detection approach to multiple classifications of breast masses. We tried to separate and intelligently recognize different masses in the breast cancer by means of mammograms so that in the first step, with the pre-processing, pectoral region is segmented from other parts and different areas are primarily clustered by K-means method. In the next step, using aggregation of efficient features such as texture features, Pseudo–Zernike moments, and wavelet features will be extracted from the input image and simulated annealing algorithm will reduce the size of feature vector. The final step will be the classification of possible masses in mammogram and the assessment of its severity based on memetic meta-heuristic adaptive neuro-based fuzzy inference system in which the optimizer is shuffled frog-leaping algorithm. The proposed method is evaluated using 322 mammogram images taken from Mini-MIAS database, which contain a variety of possible masses in mammograms. We compare our model with similar algorithms and several state-of-the-art methods through a comprehensive set of experiments. In this approach, the focus is on providing a hybrid algorithm for accurate detection and extraction of masses in mammography, with the approach that the physician can predict both the potential disease stage and type of tumor.

Orthogonal moment feature extraction and classification of melanoma images

This paper offers idea of orthogonal moments (OM) such as, Zernike Moments (ZM), and Pseudo Zernike Moments (PZM) for the analysis of melanoma images. Scale and phase invariance have been tested by varying the image sizes 32x32, 64x64, 128x128, and 256x256 and by varying phase angle from 10θ to 80θ degrees for the melanoma images. Magnitude of moment features have been extracted up to 32 orders for the cases m=0 and m=2. These extracted moment features are optimized by Particle Swarm Optimization (PSO) and classified by Support Vector Machine (SVM) and resultant achieved accuracy is 91.24%, sensitivity is 86.78%, and specificity is 88.76% which is better than existing techniques.

Novel Image Watermarking Approach against Noise and RST Attacks

Digital watermarking is used for copyright protection of intellectual properties and hence it is important to protect and recover data from attacks. Existing systems work on and recover the image from single attacks. This paper aims at proposing a technique for retrieval of cover image and watermarked data from dual attacks like rotation and noise attacks. The proposed system takes as input, Color images and then embeds data using alpha blending method. And also tries to recover from dual attacks using median filtering and pseudo Zernike moment. Proposed approach selects LH band from the 4 sub bands image divided into using DWT and for reducing noise from the image SVD is used. Proposed approach is giving better results in terms of PSNR and MSE as compared to other existing systems using QWT.

Research and Experiment of Radar Signal Support Vector Clustering Sorting Based on Feature Extraction and Feature Selection

The result of radar signal sorting directly affects the performance of electronic reconnaissance equipment. Sorting method based on intra-pulse features has become a research focus in recent years. However, as the number of extracted features increases, the dimension of the feature vector becomes higher and higher. And too many dimensional feature vectors would make the complexity of the sorting algorithm increase geometrically. In this way, feature selection becomes more and more necessary. Combining the latest research on fuzzy rough sets, this paper proposes two feature selection methods, namely two-steps attribute reduction based on fuzzy dependency (TARFD) algorithm and fuzzy rough artificial bee colony (FRABC) algorithm. The TARFD method uses the candidate attribute set as starting point, according to the definition of the redundant attribute set. Then the less important attributes are successively eliminated. The FRABC method starts from the dependence degree of fuzzy rough set, and constructs a fitness function that reflects the importance of the attribute subset and the reduction rate. Based on this function, the artificial bee colony algorithm is used to reduce the attributes of the dataset. Using the TARFD and FRABC algorithms, the extracted feature sets, including entropy feature set, Zernike moment feature set, pseudo Zernike feature set, gray level co-occurrence matrix (GLCM) feature set, and Hu-invariant moment feature set are processed, then an optimal feature subset was obtained and a sorting test was performed. The results show the effectiveness of the extracted intra-pulse features and the efficiency of the feature selection algorithm.

Reconstruction Error Analysis of Skin Lesion Images using Orthogonal Moments

Orthogonal moments (OMs) are amongst the superlative region centered shape descriptors. These OMs retain lowest facts redundancy. Zernike Moments (ZM) and pseudo Zernike Moments (PZM) are tested with respect to rotation invariance, and scale invariance for skin lesion images. Image reconstruction is executed for various orders of two different orthogonal moments; ZM and PZM. Reconstruction errors are also computed. This paper examines the impact of these errors on the features of OMs and executes a relative study of these errors on the precise calculation of the two major OMs: ZMs and PZMs.

Restoration of defaced serial numbers using lock-in infrared thermography (Part II)

This paper details continuing work on the development of a substantive non-destructive method to recover defaced serial numbers stamped or laser engraved into metallic objects based on lock-in infrared thermography. This method relies on the existence of a local zone of plastic strain created from stamping pressures in mechanically stamped pieces and a heat-affected zone in laser engraved samples, both extending to depths below the visible characters. The grain structure within these zones is dislocated due to the external forces applied. These deformed areas are exposed to the surface when the serial numbers are defaced. Infrared thermography utilises the change in thermal conductivity, based on local variation in the thermal gradient from thermal energy applied at the surface. Observation of the thermal gradient at the surface as it propagates through the object allows for identification of these deformed regions and subsequent recovery of the serial number. Principal component analysis is used to enhance the thermographic images. Pseudo Zernike moments and subsequently multiple similarity measures are utilised to identify the numbers based on a reference library of numbers. Several fusion rules are used to obtain a consensus across the similarity measures. This process is tested on several datasets including stamped numbers on a gun barrel, laser engraved numbers on a needle holder and the defaced vehicle identification number of a stolen motorcycle.

Ensembles of classifiers for improved SAR image recognition using pseudo Zernike moments

In this paper, a new approach for improving the classification of different kinds of ground vehicles from moving stationary target acquisition and recognition images is proposed. Pseudo Zernike moments are used for feature extraction due to its capability of being scale, rotation, and translation invariant. To benefit from the diversities of regions we utilize both target and shadow regions as separate regions of interest for vehicle representation. Region of interests in the form of “area,”“boundary,” and “texture” are used for extraction. Extracted features from target and shadow regions of area, boundary, and texture are fused and fed to different classifiers. Five classifiers with different properties are adopted, including support vector machine, which is a parametric classifier that can control overfitting, in contrast to the decision tree, which is a nonparametric classifier, linear discriminant analysis, and k-nearest neighbor, which have cheaper computational cost, and random forest, which is an appropriate classifier for estimating outlier and missing data. In order to improve the overall performance of target recognition, we proposed a novel approach in which first we define six regions and fuse them to a single vector. Then fused feature vectors are fed to classifiers and the final decision is generated using majority voting. Experimental results justify that by combining decision with majority voting the performance is improved.

Pseudo Zernike moments-based approach for text detection and localisation from lecture videos

Scene text presents challenging characteristics mainly related to acquisition circumstances and environmental changes resulting in low quality videos. In this paper, we present a scene text detection algorithm based on pseudo Zernike moments (PZMs) and stroke features from low resolution lecture videos. Algorithm mainly consists of three steps: slide detection, text detection and segmentation and non-text filtering. In lecture videos, slide region is a key object carrying almost all important information; hence slide region has to be extracted and segmented from other scene objects considered as background for later processing. Slide region detection and segmentation is done by applying pseudo Zernike moment's based on RGB frames. Text detection and extraction is performed using PZMs segmentation over V channel of HSV colour space, and then stroke feature is used to filter out non-text region and to remove false positives. The algorithm is robust to illumination, low resolution and uneven luminance from compressed videos. Effectiveness of PZM description leads to very few false positives comparing to other approached. Moreover resulting images can be used directly by OCR engines and no more processing is needed.

Fast and stable algorithms for high-order Pseudo Zernike moments and image reconstruction

Pseudo Zernike moments are broadly applied in the fields of image processing and pattern recognition. In this paper, we propose fast and stable methods for calculating high-order Pseudo Zernike moments. A new recurrence is introduced with the addition of a proof. Combining with the Farey sequence, the proposed method is adequate for fast computation. Furthermore, by collaborating with some procedures such as filter method or patch method, we can enhance the accuracy dramatically. The experimental results show that it takes 8.360 s to compute the top 500-order Pseudo Zernike moments of an image with 512 by 512 pixels using the proposed method. Its normalized mean square error is 0.000564363 if 500-order moments are used to reconstruct the image. When computing high-order Pseudo Zernike moments, the proposed filter method surpasses other compared methods in both speed and accuracy.

An Efficient ROI Image Watermarking on Geometric Attacks

Watermarking is raised to apparatus for the Privacy of Intellectual Property Rights (IPR) of combination dates. In this paper, in the starting we have to fill the user name field and password field which will be secure afterwards that it will be make QR-code using zxing library and it is transformed into binary patterns for share-1 that is called Visual cryptography algorithm. Now share-2 is store into server database and it will be furthered use in future situation at receiver way. Now share-1 is hiding into the LL-Band with the help of DWT-SVD into block manner with Pseudo Zernike moment. Then it is sent to the network or internet. As in network there are many unlike attackers whose apply any Rotation, Scaling or Translation attacks on the hiding image. Attack image is expected at the end side or receiver side. To get prevent against attacks here at the starting stage use Pseudo Zernike moment then after Surf based feature extraction and it will recover the attacks pixel and scaling parameters value and using affine transformation recover the rotational parameters value. So then scale value and angle value is apply on attack image recovered watermark image. Now using DWT+SVD block method extract the water mark share-1. So on system with share-1 and another share-2 will be in server side so now by using EX-OR process for getting QR-Code. At the last stage QR-code is translated and fill field user name and password vale to login the system successfully.

Audio-Visual Speech Recognition based on Machine Learning approach

Audio-visual speech recognition by machine plays an important role when research in automatic speech recognition reaches its highest performance. Audio alone also gives good performance, but adding the visual information potentially gives more convenient recognition system when an audio signal degrades in a noisy environment and may vary because of the environmental channel. This paper proposes an audio-visual automatic speech recognition (AV-ASR) system based on machine learning approaches. Visual information is captured from lip contour. Pseudo Zernike moments (PZMs) and 19th order Mel frequency cepstral coefficients (MFCCs) are extracted to obtain visual information and audio feature respectively. Machine learning approach, artificial neural networks (ANN) and support vector machines (SVM) are used to recognise speech for audio and visual modality. After the individual recognition of two systems, a combined decision is taken. This paper also evaluates the individual performance of both audio and visual speech recognition by machine learning approach.