Professor Roberto Rosas, Electrical & Computer Engineering Department at UDLAP

Ph. D. Degree in Electrical Engineering from University of Washington (Seattle, Washington, U. S. A.) in 1999. Full-time Professor at the Department of Electrical & Computer Engineering, Universidad de las Américas-Puebla (Puebla, México) since 2000. He also holds the position of Chair of Graduate Studies in the same department since 2012. Visiting Professor at the Department of Diagnostic Radiology in Yale University (New Haven, Connecticut, U. S. A.) in 2012. Two-time Fulbright Scholar as student at University of Washington in 1996-1999 and as visiting professor at Yale in 2012, respectively. Short-term visits for research and lecturing at the Department of Computer Science in University College London (London, United Kingdom) in 2018, Department of Computer Science in Durham University (Durham, United Kingdom) in 2018, Université de Montréal (Montréal, Quebec, Canada) in 2017 and Appalachian State University (Boone, North Carolina, U. S. A.) in 2010.

Recipient of funds from the Mexican Government to increase the coverage area of the Telecommunications Network in the State of Puebla in Mexico by introducing multiple wireless links (2009-2010). As a result of this project, internet services for data, voice and video are reaching isolated communities with different applications such as in education and health. He has also collaborated with faculty and students from Appalachian State University to provide a health clinic in a rural community (Puebla, México) with technology to transform solar radiation into energy for hot water and electricity (2010-2011). Involvement with people from research groups such as the Image Processing and Analysis Group at Yale and the Vascular Imaging Lab at University of Washington.

Research interests in Signal Processing, Computer Vision, Pattern Recognition, Machine Learning and Medical Image Analysis. Ongoing research has been applied to ultrasound image segmentation, forest fire detection from video signals, micro-aneurysm detection in fundus eye images to assist in the diagnosis of diabetic retinopathy, recognition of human actions in video signals, predictive models for time series in finance (stock market), prediction of epileptic seizures based on brain waves, detection of deafness in newborn cries, alpha matte extraction from green screen images, detection of micro-calcifications on mammograms as a pre-diagnosis tool of breast cancer, transiting exo-planet identification. Research results have appeared in the following selected publications and research projects:

Journal Papers

  • O. Starostenko-Basarab, C. Pérez-Cruz, V. Alarcón-Aquino, R. Rosas-Romero, "Real-time facial expression recognition using local appearance-based descriptors", Journal of Intelligent & Fuzzy Systems, 2019.
  • R. Rosas-Romero, O. López-Rincón, O. Starostenko-Basarab, "Fully automatic alpha matte extraction using artificial neural networks", Neural Computing & Applications, 2019 (paper).
  • J. Hernández-Capistrán, J. Martínez-Carballido, R. Rosas-Romero, "False positive reduction by an annular model as a set of few features for microcalcification detection to assist early diagnosis of breast cancer", Journal of Medical Systems, vol. 42, no. 134, pp. 1-9, 2018 (paper).
  • L. Peralta-Malváez, O. López-Rincón, E. D. Rojas-Velázquez, L. O. Valencia-Rosado, R. Rosas-Romero, G. Etecheverry, "Newborn cry nonlinear features extraction and classification", Journal of Intelligent & Fuzzy Systems, vol. 34, pp. 3281-3289, 2018 (paper).
  • R. Rosas-Romero, A. Díaz-Torres, G. Etcheverry, "Forecasting of stock return prices with sparse representation of financial time series over redundant dictionaries", Expert Systems with Applications, vol. 57, pp. 37-48, 2016 (paper).
  • R. Rosas-Romero, J. Martínez-Carballido, J. Hernández-Capistrán, L. J. Uribe-Valencia, "A method to assist in the diagnosis of early diabetic retinopathy: Image processing applied to detection of microaneurysms in fundus images", Computerized Medical Imaging and Graphics, vol. 44, pp. 41-53, 2015 (paper).
  • G. Castro-Muñoz, J. Martínez-Carballido, R. Rosas-Romero, "A human action recognition approach with a novel reduced feature set based on the natural domain knowledge of the human figure", Journal of Signal Processing: Image Communication, vol. 30, pp. 190-205, 2015 (paper).
  • R. Rosas-Romero, "Remote detection of forest fires from video signals with classifiers based on K-SVD learned dictionaries", Journal of Engineering Applications of Artificial Intelligence, vol. 33, pp. 1-11, 2014 (paper).
  • R. Rosas-Romero, H. D. Tagare, "Segmentation of endocardium in ultrasound images based on sparse representation over learned redundant dictionaries", Journal of Engineering Applications of Artificial Intelligence, vol. 29, pp. 201-210, 2014 (paper).

Conference Talks and Publications

Research

Example of a light curve. As the exoplanet orbits the star, different brightness values are obtained.
  • Transiting exo-planet identification using machine learning techniques

Spatial missions such as the Kepler mission, and the Transiting Exoplanet Survey Satellite (TESS) mission, have encouraged data scientists to analyze light curve datasets. The purpose of analyzing these data is to look for planet transits, with the aim of discovering and validating exoplanets, which are planets orbiting outside our Solar System. Manual examination of these datasets is a task that requires big quantities of time and effort, and therefore is prone to errors. As a result, the application of machine learning methods has become more common on exoplanet identification and categorization research. This work consists of an analysis on different exoplanet identification algorithms based on machine learning, some of which even validated new exoplanets. We are claiming that multi-resolution analysis approaches should be appropriate for exoplanet identification because of the characteristics of light curves and transiting exoplanet parameters.

Results of fully-automatic alpha matte extraction and compositing of extracted foreground on new background scenes.
  • Fully automatic alpha matte extraction in green screen images using artificial neural networks

The alpha matte is a two-dimensional map that is used to combine two images, one containing a foreground and the other containing a background, a process known as digital compositing. Alpha matte extraction is performed on green-screen images and requires user interaction to tune parameters in different pre-processing and post-processing stages to refine an alpha matte. This work tackles the problem of fully-automatic extraction of the foreground on a green-screen image along with the extraction of the corresponding alpha matte, a process also known as pulling a matte. The method is based on learning machine that assigns an alpha value, from a discrete set of ten alpha values {0, 0.1, 0.2, …, 0.9}, to each patch on a green-screen image. The approach for assigning an alpha value to a patch is based on a set of features that enhance discrimination between foreground and background. Prior to alpha matte extraction, the classifier is trained to learn to separate foreground objects from green-screen backgrounds as well as to generate the corresponding alpha matte map required for subsequent digital compositing. We tested the proposed method on high-definition (HD) green-screen images, corresponding to two different sequence cases (TOY CAR ROTO & GODIVA MEDIUM), both cases from a public data set provided by Hollywood Camera Work LLC. HD green-screen images, from each particular case, have limitations that are not good enough for film production. In addition, a data set with 64 images was generated to test how the proposed approach handles alpha matte extraction under unsuitable conditions such as short separation distance between the subject and the green screen. The project also provides, for the case of the public data set, a quantitative comparison between the alpha matte, extracted by means of the proposed approach, and that generated by the application Adobe After Effects CC, which has the disadvantage of demanding a large amount of user interaction. Collaboration with Omar López-Rincón & Dr. Oleg Starostenko-Basarab.

Publications: R. Rosas-Romero, O. López-Rincón, O. Starostenko-Basarab, "Fully automatic alpha matte extraction using artificial neural networks", Neural Computing & Applications, 2019 (paper).

R. Rosas-Romero, O. López-Rincón, E. D. Rojas-Velázquez, N. P. Jacobo-Aispuro, "Learning matte extraction in green screen images with MLP classifiers and the back-propagation algorithm", Proceedings of the 26th International Conference on Electronics, Communications and Computers(CONIELECOMP 2016), San Andrés Cholula, Puebla, México, 2016.

Cumulative return gain curves obtained by following a predictive model based on an artificial predictor (orange) vs. the market (blue).
  • Forecasting of stock return prices with sparse representation of financial time series over redundant dictionaries

This project introduces the theory, methodology and application of a new predictive model for time series within the financial sector, specifically data from 20 companies listed on the U. S. stock exchange market. The proposed method is based on learned redundant dictionaries for sparse representation of financial time series. The methodology is conducted by finding the optimal set of atoms for the predicting model following two directions for the generation of dictionaries; by extraction of atomsfrom past daily return price values to build untrained dictionaries and by atom extraction followed by training of dictionaries though K-SVD. Prediction of financial time series is a periodic process where each cycle consists of two stages: (1) training of the model to learn the dictionary that maximizes the probability of occurrence of an observation sequence of return values, (2) prediction of the return value for the next coming trading day. After prediction, the two stages are alternatively repeated by using an adjusted sequence of observations that adds the newest observed return value and drops the oldest observed return value from the sequence (window shift). The motivation for such research is the fact that a tool, which might generate confidence of the potential benefits obtained from using formal financial services, would encourage more participation in a formal system such as the stock market. Theory, issues, challenges and results related to the application of sparse representation to the prediction of financial time series, as well as the performance of the method, are presented.

Publications: R. Rosas-Romero, A. Díaz-Torres, G. Etcheverry, "Forecasting of stock return prices with sparse representation of financial time series over redundant dictionaries", Expert Systems with Applications, vol. 57, pp. 37-48, 2016 (paper).

R. Rosas-Romero, J. P. Medina-Ochoa, "Learning financial time series for prediction of the stock exchange market", Proceedings of the 34th International Conference on Computers and their Applications (CATA 2019), Honolulu, Hawaii, U. S. A., 2019.

Original image (upper panel) and result of detection of candidates to micro-aneurysms (lower panel).
  • A method to assist in the diagnosis of early diabetic retinopathy: Image processing applied to detection of microaneurysms in fundus images

Diabetes increases the risk of developing any deterioration in the blood vessels that supply the retina, an ailment known as Diabetic Retinopathy (DR). Since this disease is asymptomatic, it can only be diagnosed by an ophthalmologist. However, the growth of the number of ophthalmologists is lower than the growth of the population with diabetes so that preventive and early diagnosis is difficult due to the lack of opportunity in terms of time and cost. Preliminary, affordable and accessible ophthalmological diagnosis will give the opportunity to perform routine preventive examinations, indicating the need to consult an ophthalmologist during a stage of non-proliferation. During this stage, there is a lesion on the retina known as microaneurysm (MA), which is one of the first clinically observable lesions that indicate the disease. In recent years, different image processing algorithms, which allow the detection of the DR, have been developed; however, the issue is still open since acceptable levels of sensitivity and specificity have not yet been reached, preventing its use as a pre-diagnostic tool. Consequently, this work introduces a new approach for MA detection based on (1) reduction of non-uniform illumination; (2) normalization of image grayscale content to improve dependence of images from different contexts; (3) application of the bottom-hat transform to leave reddish regions intact while suppressing bright objects; (4) binarization of the image of interest with the result that objects corresponding to MAs, blood vessels, and other reddish objects (Regions of Interest - ROIs) are completely separated from the background; (5) application of the hit-or-miss Transformation on the binary image to remove blood vessels from the ROIs; (6) two features are extracted from a candidate to distinguish real MAs from FPs, where one feature discriminates round shaped candidates (MAs) from elongated shaped ones (vessels) through application of Principal Component Analysis (PCA); (7) the second feature is a count of the number of times that the radon transform of the candidate ROI, evaluated at the set of discrete angle values {0°, 1°, 2°, …, 180°}, is characterized by a valley between two peaks. The proposed approach is tested on the public databases DiaretDB1 and Retinopathy Online Challenge (ROC) competition. The proposed MA detection method achieves sensitivity, specificity and precision of 92.32%, 93.87% and 95.93% for the diaretDB1 database and 88.06%, 97.47% and 92.19% for the ROC database. Theory, results, challenges and performance related to the proposed MA detecting method are presented.

Publication: R. Rosas-Romero, J. Martínez-Carballido, J. Hernández-Capistrán, L. J. Uribe-Valencia, "A method to assist in the diagnosis of early diabetic retinopathy: Image processing applied to detection of microaneurysms in fundus images", Computerized Medical Imaging and Graphics, vol. 44, pp. 41-53, 2015 (paper).

Monitoring System for Remote Detection of Forest Fires.
Smoke detection under high illumination.
  • Remote detection of forest fires from video signals with classifiers based on K -Singular Value Decomposition (K-SVD) learned dictionaries

In this project a method for remote detection of forest fires in video signals from surveillance cameras is introduced. The idea is based on learned redundant dictionaries for sparse representation of feature vectors extracted from image patches on three different regions; smoke, sky and ground. A testing image patch is assigned to the region for which the corresponding dictionary gives the best sparse representation during segmentation. To further reduce the presence of misclassified patches, a spatio-temporal cuboid of patches is built around a classified patch to take a majority vote in the set of classes inside the cuboid. To reduce the number of false positives there is a verification process to determine if a region of interest is growing. Theory, results, issues and challenges related to the implementation of the forest fire monitoring system, and performance of the method are presented.

Publications: R. Rosas-Romero, "Remote detection of forest fires from video signals with classifiers based on K-SVD learned dictionaries", Journal of Engineering Applications of Artificial Intelligence, vol. 33, pp. 1-11, 2014 (paper).

R. Rosas-Romero, "Detection of forest fires from video signals with sparse representation over dictionaries", Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017), San Diego, California, U. S. A., 2017.

Results of segmentation based on sparse representation: Original Image (above) & Segmented Image (bellow).
  • Segmentation of endocardium in ultrasound images based on sparse representation over learned redundant dictionaries

This project tackles the problem of segmenting the endocardium in 2-D short-axis echocardiographic images from rats by using the sparse representation of feature vectors over learned dictionaries during classification. We highlight important aspects of the application of the theory of sparse representation and dictionary learning to the problem of ultrasound image segmentation. Experiments were conducted following two directions for the generation of dictionaries for myocardium and blood pool regions; by manual extraction of image patches to build untrained dictionaries and by patch extraction followed by training of dictionaries. The results obtained from different learned dictionaries are compared. During classification of an image patch, instead of using features of the patch alone, features of neighboring patches are combined.

Publication: R. Rosas-Romero, H. D. Tagare, "Segmentation of endocardium in ultrasound images based on sparse representation over learned redundant dictionaries", Journal of Engineering Applications of Artificial Intelligence, vol. 29, pp. 201-210, 2014 (paper).

Illustration of different states (pre-ictal, ictal, inter-ictal) in one single EEG channel, one HbO channel, and one HbR channel, extracted from an epileptic patient.
  • Prediction of epileptic seizures based on convolutional neural networks (CNN) and functional Near Infra Red Spectroscopy (fNIRS) signals

This work presents a detailed description of the implementation of the learning algorithm for a Deep Learning Machine (DLM), specifically, a Convolutional Neural Network(CNN), which is effectively applied to the prediction of epileptic seizures from functional Near Infrared Spectroscopy (fNIRS) recordings, an optical modality for recording of brain waves. A CNN is suitable for this application, instead of other learning machines, since fNIRS recordings are characterized by very high dimensionality, given that there are hundreds of fNIRS channels and that at any time position these signals are represented as two-dimensional tensors. The training of the CNN is based on the back propagation algorithm to update kernel weights in convolutional layers and synaptic weights in classification layers. This work presents the required formulations to update weights over all the layers of the network. Application of CNN to fNIRS recordings showed an accuracy ranging between 96.9% and 100%, depending on the subject. The most important aspect of obtaining these results is the combination of fNIRS signals with the particular CNN algorithm. This signal modality has not been used in epileptic seizure prediction and this work pretends to be one of the first to use this modality and deep learning to address the problem of seizure prediction.

Publication: A. Flores-Castro, K. Peng, D. K. Nguyen, F. Lesage, P. Pouliot, R. Rosas-Romero, E. Guevara, "Detecting epileptic seizures in advance using optical and electrical recordings", Proceedings of the 27th International Conference on Electronics, Communications and Computers (CONIELECOMP 2017), San Andrés Cholula, Puebla, México, 2017.

Overview of the proposed human action recognition method: extraction and tracking of regions of interest, feature extraction and classification.
Representation of a silhouette as three rectangular regions.
Outline of the bounding box tracker.
  • A human action recognition approach with a reduced feature set based on the natural domain knowledge of the human figure

Current video surveillance systems are not designed to raise an automatic alert in case of situations that put people lives at risk such as accidents, assaults and terrorism among others. This is due to the fact that these systems are not able to analyze huge amounts of video signals at higher processing speed where these signals come from cameras installed in the worldwide network. Faced with this situation, scientific communities are combining efforts to design algorithms and hardware to accelerate the processing of video signals. However, most of the methods proposed to date are too complex to be implemented in hardware at the place where the video camera is installed. In this paper, we report a significantly reduced feature set to design an analysis algorithm of significant less complexity which recognizes human actions from video sequences. The proposed method is based on the natural domain knowledge of the human figure such as proportions of the human body and foot positions. The analysis is characterized by working on sub-sequences of the entire video signals, processing a small fragment of the whole image, estimating the location of the region of interest, using simple operations (sum, subtraction, multiplications, divisions), extracting a reduced number of features per frame (6 features), and using a combination of four linear classifiers (one perceptron and three support vector machines) with a hierarchical structure. The method is evaluated on two of the datasets cited in the human action recognition literature, the Weizmann and the UIUC datasets. Results show that for the case of the Weizmann dataset, the correct classification rate (CCR) is 99.95% when the LOOCV Protocol is used and 98.38% for the case of Protocol 60-40, which is comparable or even higher than that of current state-of-the-art methods. Confusion matrices were also obtained for the UIUC dataset, where the obtained CCR is 100% for the case of the LOOCV Protocol and 99.35% when Protocol 60-40 is used. The experimental results are promising with much fewer features (between 85 and 113 times less features), compared with other methods, and the possibility of processing more than 200 fps.

Publication: G. Castro-Muñoz, J. Martínez-Carballido, R. Rosas-Romero, "A human action recognition approach with a novel reduced feature set based on the natural domain knowledge of the human figure", Journal of Signal Processing: Image Communication, vol. 30, pp. 190-205, 2015 (paper).

Stages for detection of micro-calcifications as a tool to assist in diagnosis of breast cancer: cluster identification, segmentation, binarization, feature extraction, and classification .
  • False positive reduction by an annular model as a set of few features for microcalcification detection to assist early diagnosis of breast cancer

Early automatic breast cancer detection from mammograms is based on the extraction of lesions, known as microcalcifications (MCs). This research proposes a new and simple system for microcalcification detection to assist in early breast cancer detection. This work uses the two most recognized public mammogram databases, MIAS and DDSM. The MC detection method is based on (1) Beucher gradient for detection of regions of interest (ROIs), (2) an annulus model for extraction of few and effective features from candidates to MCs, and (3) one classification stage with two different classifiers, k Nearest Neighbor (KNN) and Support Vector Machine (SVM). For dense mammograms in the MIAS database, the performance metrics achieved are sensitivity of 0.9835, false alarm rate of 0.0083, accuracy of 0.9835, and area under the ROC curve of 0.9980 with a KNN classifier. The proposed MC detection method, based on a KNN classifier, achieves, a sensitivity, false positive rate, accuracy and area under the ROC curve of 0.9813, 0.0224, 0.9795 and 0.9974 for the MIAS database; and 0.9035, 0.0439, 0.9298 and 0.9759 for the DDSM database. By slightly reducing the true positive rate the method achieves three instances with false positive rate of 0:2 on fatty mammograms with KNN and SVM, and one on dense with SVM. The proposed method gives better results than those from state of the art literature, when the mammograms are classified in fatty, fatty-glandular, and dense.

Publication: J. Hernández-Capistrán, J. Martínez-Carballido, R. Rosas-Romero, "False positive reduction by an annular model as a set of few features for microcalcification detection to assist early diagnosis of breast cancer", Journal of Medical Systems, vol. 42, no. 134, pp. 1-9, 2018 (paper).

Interests

Academy Awards

Photography