IUST Pattern Recognition Projects

1) Sentiment Analysis using SVM

1.1) Problem definition

TO-DO

1.2) Dataset

The dataset was used in this project contains more than 50000 movie reviews, and it split up into Train, Validation, and Test sets already. All the movie reviews are long sentences (most of them are longer than 200 words). Also, each review was labeled as 1 (positive review) or 0 (negative review). The dataset was originally introduced in [1], but its .csv file can be downloaded from here.

Movie Reviews Dataset

1.3) Solution

TO-DO

References

  1. Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. (2011). Learning Word Vectors for Sentiment Analysis. The 49th Annual Meeting of the Association for Computational Linguistics (ACL 2011).

2) Boosting for Imbalanced Data

2.1) Problem definition

TO-DO

2.2) Dataset

TO-DO

2.3) Solution

TO-DO

References

TO-DO

3) Offline Signature Verification using Deep Learning

3.1) Problem definition

An offline signature verifier model should be trained using the Convolutional Neural Networks (CNNs). The problem can be interpreted in many ways, such as classifying signatures based on their signatories or detecting that a signature is genuine or forgery. But, the first interpretation was considered at the implementation.

3.2) Dataset

The UTSig [1] dataset was used in this project, and it can be downloaded from here. UTSig has 115 classes containing: 27 genuine signatures, 3 opposite-hand signed samples, and 42 simple forgeries. Each class belongs to one specific authentic person.

3.3) Solution

InceptionV3

The Inception V3 was used as a feature extractor in this project. It's trained by Google on more than a million images from the ImageNet database to classify images into 1000 object categories.

References

  1. Amir Soleimani and Kazim Fouladi and Babak Nadjar Araabi (2016). UTSig: A Persian Offline Signature Dataset. https://arxiv.org/abs/1603.03235

Course Information

  • Pattern Recognition
  • Fall 2020
  • Dr. Morteza Analoui [Scopus]
  • Iran University of Science and Technology (IUST) [Website]
  • Department of Computer Engineering [Website]