List of subject articles Pattern Recognition


    • Open Access Article

      1 - Facial Images Quality Assessment based on ISO/ICAO Standard Compliance Estimation by HMAX Model
      Azamossadat Nourbakhsh Mohammad-Shahram Moin Arash  Sharifi
      Facial images are the most popular biometrics in automated identification systems. Different methods have been introduced to evaluate the quality of these images. FICV is a common benchmark to evaluate facial images quality using ISO / ICAO compliancy assessment algorit Full Text
      Facial images are the most popular biometrics in automated identification systems. Different methods have been introduced to evaluate the quality of these images. FICV is a common benchmark to evaluate facial images quality using ISO / ICAO compliancy assessment algorithms. In this work, a new model has been introduced based on brain functionality for Facial Image Quality Assessment, using Face Image ISO Compliance Verification (FICV) benchmark. We have used the Hierarchical Max-pooling (HMAX) model for brain functionality simulation and evaluated its performance. Based on the accuracy of compliancy verification, Equal Error Rate of ICAO requirements, has been classified and from those with higher error rate in the past researches, nine ICAO requirements have been used to assess the compliancy of the face images quality to the standard. To evaluate the quality of facial images, first, image patches were generated for key and non-key face components by using Viola-Jones algorithm. For simulating the brain function, HMAX method has been applied to these patches. In the HMAX model, a multi-resolution spatial pooling has been used, which encodes local and public spatial information for generating image discriminative signatures. In the proposed model, the way of storing and fetching information is similar to the function of the brain. For training and testing the model, AR and PUT databases were used. The results has been evaluated by FICV assessment factors, showing lower Equal Error Rate and rejection rate, compared to the existing methods. Manuscript Document
    • Open Access Article

      2 - An Efficient Method for Handwritten Kannada Digit Recognition based on PCA and SVM Classifier
      Ramesh G Prasanna  G B Santosh  V Bhat Chandrashekar  Naik Champa  H N
      Handwritten digit recognition is one of the classical issues in the field of image grouping, a subfield of computer vision. The event of the handwritten digit is generous. With a wide opportunity, the issue of handwritten digit recognition by using computer vision and m Full Text
      Handwritten digit recognition is one of the classical issues in the field of image grouping, a subfield of computer vision. The event of the handwritten digit is generous. With a wide opportunity, the issue of handwritten digit recognition by using computer vision and machine learning techniques has been a well-considered upon field. The field has gone through an exceptional turn of events, since the development of machine learning techniques. Utilizing the strategy for Support Vector Machine (SVM) and Principal Component Analysis (PCA), a robust and swift method to solve the problem of handwritten digit recognition, for the Kannada language is introduced. In this work, the Kannada-MNIST dataset is used for digit recognition to evaluate the performance of SVM and PCA. Efforts were made previously to recognize handwritten digits of different languages with this approach. However, due to the lack of a standard MNIST dataset for Kannada numerals, Kannada Handwritten digit recognition was left behind. With the introduction of the MNIST dataset for Kannada digits, we budge towards solving the problem statement and show how applying PCA for dimensionality reduction before using the SVM classifier increases the accuracy on the RBF kernel. 60,000 images are used for training and 10,000 images for testing the model and an accuracy of 99.02% on validation data and 95.44% on test data is achieved. Performance measures like Precision, Recall, and F1-score have been evaluated on the method used. Manuscript Document