Public Presentations
Several public presentations have been done in the last years. Some of them are as a keynote speaker or speaker in international conferences in English… other ones as a local speaker at the University in Spanish. Here you can find the most important presentations. See more…
Code & Datasets
The following are the repositories of the public codes and/or datasets of our projects:
+ Skin Lesion Recognition using Deep Learning: 50 Ways to Choose Your Model
Python code of 50 deep learning models in Google Colab:
- CNN’s and pretrained models (from library TorchVision: ResNet, MobileNet, SqueezeNet, AxelNet, VGG, etc.)
- ARLNET (from library Vipermdl/ARL)
- EfficientNet (from library efficientnet_pytorch)
- Visual Transformer (from library HuggingFaces)
D Mery, P Romero, G Garib, A Pedro, MP Salinas, J Sepulveda, L Hidalgo, C Prieto, C Navarrete-Dechent (2022): On Skin Lesion Recognition using Deep Learning: 50 Ways to Choose Your Model, Pacific-Rim Symposium on Image and Video Technology (PSIVT 2022).
+ Low-Resolution Face Re-identification with High-Resolution-Mapping
Dataset used in the paper:
L Prieto, S Pulgar, P Flynn, D Mery (2022): On Low-Resolution Face Re-identification with High-Resolution-Mapping, Pacific-Rim Symposium on Image and Video Technology (PSIVT 2022).
+ True Black-Box Explanation on Facial Analysis
Python code in Google Colab used for the paper
Mery, D. (2022): True Black-Box Explanation on Facial Analysis. In 17th IEEE Computer Society Workshop on Biometrics 2022 with CVPR2022.
+ Black-Box Explanation for Face Verification
Python code in Google Colab used for the paper
Mery, D.; Morris, B. (2022): On Black-Box Explanation for Face Verification. In 2022 IEEE Winter Conference on Applications of Computer Vision (WACV2022).
+ PyXvis Library
Python Library used in the examples of the book Computer Vision for X-Ray Testing (2nd Edition). It contains more than 150 functions for image processing, feature extraction, feature transformation, feature analysis, feature selection, data selection and generation, classification, deep learning, GAN, clustering, simulation, performance evaluation, multiple-view analysis, image sequence processing and tracking with geometrical constraints. See repository.
+ X-ray detection in 3D
Supplementary material for the paper: Riffo, V.; Godoy, I.; and Mery, D. (2019): Handgun Detection in Mono-energetic Multiple X-ray Views Based on 3D Object Recognition, Journal of Nondestructive Evaluation. 2019 See code and images.
+ Face-R
This is the database and the code for the Automated Student System that we presented at WACV 2019. The database contains full-annotaed 25 sessions of a classroom with around 70 students. The session images were taken in 15 week during a semester at the School of Engineering at the Catholic University of Chile.
Mery, D.; Mackenney, I.; and Villalobos, E. Student Attendance System in Crowded Classrooms using a Smartphone Camera. In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV2017), 2019. [ PDF ]
- Simple implementation: See GitHub repository.
- Full implementation and dataset: See GitHub repository.
- Registration for using App: Fill Form
- See the video on YouTube.
+ GDXray database
As a service to the X-ray testing and Computer Vision communities, we collected more than 19.400 X-ray images for the development, testing, and evaluation of image analysis and computer vision algorithms. The X-ray images included in GDXray can be used free of charge, for research and educational purposes only. Redistribution and commercial use are prohibited. See more…
+ Toolbox Balu
Matlab toolbox for image processing, feature extraction, feature transformation, feature analysis, feature selection, data selection and generation, classification, clustering, performance evaluation, multiple-view analysis, image sequence processing and tracking with geometrical constraints. It contains more than 200 functions. See more...
+ Toolbox Xvis
Matlab toolbox for X-ray testing with computer vision with more than 150 functions for image processing, feature extraction, feature transformation, feature analysis, feature selection, data selection and generation, classification, clustering, simulation, performance evaluation, multiple-view analysis, image sequence processing and tracking with geometrical constraints. See more...
+ ASR+
This is the supplementary material for our algorithm ‘Adaptive Sparse Recognition with Random Patches for Recognition of Facial Attributes and Face Recognition’.
> Code, datasets and examples: See GitHub repository.
ASR+ used in recognition of facial attributes was presented at ECCV2014 Workshop on Soft-Biometrics (see slides and paper –best paper award–). ASR+ used in face recognition will be presented at WIFS2014 (see paper).
+ AISM
This is the suplementary material of our algorithm ‘Adapted Implicit Shape Model’ used to detect threat objects in baggage screening. Download Matlab code and images, example and paper:
Riffo, V.; Mery, D. (2015): Automated detection of threat objects using Adapted Implicit Shape Model. IEEE Transactions on Systems, Man, and Cybernetics: Systems.
+ Xdefects (Xray-Testing)
This is the suplmentary material of the paper presented at WACV-2017 that evaluates 24 different computer vision algorithms on a dataset of 47.520 cropped images that contains defects and no-defects in aluminum castings.
> Code, datasets and examples: See GitHub repository.
Testing using Computer Vision. In 2017 IEEE Winter Conference on Applications of Computer Vision, WACV2017 [ pdf ]
+ AR-LQ (Low-quality AR face images)
We release a new dataset called AR-LQ that can be used in conjunction with the well-known AR dataset to evaluate face recognition algorithms on blurred and low-resolution face images. The dataset contains five new blurred faces (at five different levels, from low to severe blurriness) and five new low-resolution images (at five different levels, from 66×48 to 7×5 pixels) for each of the hundred subjects of the AR dataset. Download dataset ARLQ.
+
This is the suplmentary material of the paper presented at ICASSP-2018. ALSR can be used for face recognition and recognition of facial attributes. In these examples, ALSR is used for face recognition (using LFW dataset), gender recognition (using AR dataset) and expression recognition (using Oulu-CASIA dataset).
> Code, datasets and examples: See GitHub repository.
Mery, D.; and Banerjee, S.: Recognition of Faces and Facial Attributes using Accumulative Local Sparse Representations. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2018), 2018. Calgary, Canada, 15-20, Apr. [ pdf ]