Impresee Labs
Cutting-edge AI research with straight application to industry.

Our Research Area
Our research is mainly related to Artificial Intelligence with emphasis in Computer vision and Natural Languale Processing. Our team works in problems related with searching by pictures and sketches, video based retrieval, and NLP for e-commerce.

Sketch Based Image Retrieval
Sketch based image retrieval (SBIR) is a growing field in computer vision that consists in retrieving a collection of photos resembling a sketch query. Aiming to make the querying process as easy as possible, the input query is formulated as a simple hand-drawing, composed uniquely of strokes. In this way, people just need to draw what they are looking for, or what they are thinking of.

Searching by Images

NLP for e-commerce
NLP deals with processing and understanding natural language data. We conduct different works aiming to improve the effectiveness of search engines through NLP based approaches.
Impresee
Research Leads
![]() |
José M. SaavedraDirector of Impresee Labs. PhD in Computer Science, University of Chile. Research Areas: Computer Vision, Deep Learning, Pattern Recognition |

José M. Saavedra
Director of Impresee Labs. PhD in Computer Science, University of Chile
Research Areas: Computer Vision, Deep Learning, Pattern Recognition
![]() |
Juan BarriosCEO of Impresee. PhD in Computer Science, University of Chile. Research Areas: , NLP |

Juan Barrios
Director of Impresee Labs. PhD in Computer Science, University of Chile
Research Areas: Computer Vision, Deep Learning, Pattern Recognition
our
Alumni
Pablo Torres
Sketch based Retrieval
Catalina Contreras
Visual Recommendation
Jean Cherubini
One-shot detection
Javier Morales
Unsupervised Learning for SBIR
Lukas Pavez
Non-Local Features
Andres Baloian
Attribute based Retrieval
Cristobal Loyola
One-Shot Detection
our
Publications
2020
|
Andre G. Hochuli, Alceu S. Britto Jr., David A. Saji, Jose M. Saavedra, Robert Sabourin, Luiz S. Oliveira, A Comprehensive Comparison of End-to-End Approaches for Handwritten Digit String Recognition.Expert Systems with Applications, 2020.
|
Úbeda, I., Saavedra, J.M., Nicolas, S., Petitjean, C., Heutte, L. Improving Pattern Spotting in Historical Documents Using Feature Pyramid NetworksPattern Recognition Letters, 2020.
|
2019
|
Fabian Souto Herrera, Jose M. Saavedra. DLDENet: Deep Local Directional Embeddings with Increased Foreground Focal Loss for object detection38th International Conference of the Chilean Computer Science Society (SCCC), 2019.
|
Úbeda, I., Saavedra, J.M.,Nicolas, S., Petitjean, C., Heutte, L. Pattern spotting in historical documents using convolutional modelsACM International Conference Proceeding Series, 2019
|
2017
|
Domingo Mery , Erick Svec , Marco Arias , Vladimir Riffo , Jose M. Saavedra , Sandipan Banerjee. Modern Computer Vision Techniques for X-Ray Testing in Baggage InspectionIEEE Transactions on Systems Man Cybernetics-Systems, 2017
|
Saavedra, Jose M. RST-SHELO: Sketch-based Image Retrieval using Sketch Tokens and Square Root NormalizationMultimedia Tools and Applications, 2017
|
2016
|
Jose M. Saavedra, Camila Alvarez. DeepSBIR: Sketch Based Image Retrieval using Deep Features1st Workshop on Deep Learning for Pattern Recognition DLPR, ICPR, Cancún, Mexico, 2016.
|
2015
|
Barrios, J.M., Saavedra, J.M. Score propagation based on Similarity Shot Graph for improving Visual Object RetrievalSLAM 2015 – Proceedings of the 2015 Workshop on Speech, Language and Audio in Multimedia, co-located with ACM MM 2015 pp. 19-22. 2015.
|
Jose M. Saavedra and Juan Manuel Barrios. Sketch based Image Retrieval using Learned KeyShapes(LKS). In Proceedings of the British Machine Vision Conference (BMVC), 2015.
|
Felipe Ramírez, Héctor Contreras, Alejandro Figueroa,Mauricio Palma. Gestión de Contactabilidad en Email para Mejorar la Experiencia del Usuario en la Industria Financiera11o Seminario Internacional “Big Data” de la Fundación Copec, Universidad Católica, 2015.
|
See more
2014
Saavedra, Jose M., Bustos, Benjamin.
Sketch-based Image Retrieval using Keyshapes
. Multimedia Tools and Applications, 2014.
DOI: 10.1007/s11042-013-1689-0
Chang, Violeta, Saavedra, Jose M., Castaneda, Victor, Sarabia, Luis, Hitschfeld, Nancy, Haertel, Steffen.
Gold-standard and improved framework for sperm head segmentation
.
Computer Methods and Programs In Biomedicine, 2014.
DOI: 10.1016/j.cmpb.2014.06.018
Li, Bo, Lu, Yijuan, Godil, Afzal, Schreck, Tobias, Bustos, Benjamin, Ferreira, Alfredo, Furuya, Takahiko, Fonseca, Manuel J., Johan, Henry, Matsuda, Takahiro, Ohbuchi, Ryutarou, Pascoal, Pedro B., Saavedra, Jose M.
A Comparison of Methods for Sketch-Based 3d Shape Retrieval
. Computer Vision and Image Understanding, 2014.
DOI: 10.1016/j.cviu.2013.11.008
Saavedra, Jose M. Handwritten Digit Recognition Based on Pooling SVM-Classifiers Using Orientation and Concavity Based Features. Lecture Notes in Computer Science, 2014.
DOI https://doi.org/10.1007/978-3-319-12568-8_80
Saavedra, Jose M.
Sketch Based Image Retrieval Using a Soft Computation of The Histogram of Edge Local Orientations (S-HELO)
. IEEE International Conference on Image Processing (ICIP), 2014.
DOI: 10.1109/ICIP.2014.7025606
Diem, Markus, Fiel, Stefan, Kleber, Florian, Sablatnig, Robert, Saavedra, Jose M., Contreras, David, Barrios, Juan Manuel, Oliveira, Luiz S. ICFHR 2014 Competition on Handwritten Digit String Recognition in Challenging Datasets (HDSRC 2014), 14TH International Conference on Frontiers in Handwriting Recognition (ICFHR), 2014.
DOI: 10.1109/ICFHR.2014.136
2013Juan Manuel Barrios, José M. Saavedra, Felipe Ramirez, David Contreras.
ORAND Team: Instance Search and Multimedia Event Detection Using k-NN Searches
.
TRECVID, 2013.
Saavedra, J.M., Bustos, B., Chang, V.
An accurate hand segmentation approach using a structure based shape localization technique
. VISAPP 2013 – Proceedings of the International Conference on Computer Vision Theory and Applications, 2013.
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84878249062&partnerID=40&md5=ad06057a567587a282c88e7bae59b53f
Li, B., Lu, Y., Godil, A.,Schreck, T., Aono, M., Johan, H., Saavedra, J.M., Tashiro, S.
Shrec’13 track: Large scale Sketch-based 3D Shape Retrieval
. 6th Eurographics Workshop on 3D Object Retrieval, 3DOR 2013, 2013.
DOI: 10.2312/3DOR/3DOR13/089-096
Join us and transform the world!