Libras-10 Dataset
Creators
- 1. Instituto Federal de Minas Gerais - Campus Ouro Preto
- 2. Machine Intelligence and Data Science (MINDS) Laboratory, Universidade Federal de Minas Gerais
- 3. Universidade Federal de Ouro Preto
Description
Brazilian Sign Language (Libras) data set with 10 signs for sign language and gesture recognition benchmark:
- to calm down (acalmar),
- to accuse (acusar),
- to annihilate (aniquilar),
- to love (apaixonado),
- to gain weight (engordar),
- happiness (felicidade),
- slim (magro),
- lucky (sortudo),
- surprise (surpresa) and
- angry (zangado).
Each one of the signs was recorded 10 times by 1 signer, totaling a database of 100 samples. The signs were captured using a RGB-D sensor (Microsoft Kinect) and processed by nuiCaptureAnalyze software. For each sign , one has rgb-d images (color_USB-VID_045E&PID_02AE-A00363A20694050A_ and depth_USB-VID_045E&PID_02AE-A00363A20694050A_), skeleton images (skeleton_USB-VID_045E&PID_02AE-A00363A20694050A_), rgb-d images containing only the face (image) and the .mat files( file "matlab" or USB-VID_045E&PID_02AE-A00363A20694050A_) which contains all the information obtained by the software that operates kinect (see http://nuicapture.com/support/how-to-export/#reading-mat-files).
Files
Files
(22.4 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:e6f958f8da598b3174a9a350865a657f
|
1.6 GB | Download |
|
md5:8a85a54cc34779053030312d87158ae4
|
2.1 GB | Download |
|
md5:d14f8200e3da6ce2fe298dfe9a458712
|
1.9 GB | Download |
|
md5:6275e36c5944c5952411c919c532fba5
|
2.1 GB | Download |
|
md5:9b3484b13534fe98fa3f7ea2173bb462
|
2.4 GB | Download |
|
md5:197d45e5cd084cbd94db6873d57dd468
|
2.3 GB | Download |
|
md5:5fa96e2ccabc264ebf00d36ae728c027
|
2.5 GB | Download |
|
md5:1312f99c27053ea848453aabbf8cc508
|
2.4 GB | Download |
|
md5:bdb240fa18fc07416acbe05a0ef6ec46
|
2.5 GB | Download |
|
md5:29a4e835ea9863b0dfb6b87dffbc817c
|
2.5 GB | Download |
Additional details
References
- Rezende, T. M.; Castro, C. L.; Almeida, S. G. M. An approach for Brazilian Sign Language (BSL) recognition based on facial expression and k-NN classifier. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES, 29. (SIBGRAPI), 2016, São José dos Campos. Proceedings... Porto Alegre: Sociedade Brasileira de Computação, 2016. On-line. IBI: <8JMKD3MGPAW/3MDH39S>. Available from: <http://urlib.net/rep/8JMKD3MGPAW/3MDH39S>.
- Rezende, T. M. (2016). Aplicação de técnicas de inteligência computacional para análise da expressão facial em reconhecimento de sinais de libras, Master's thesis, Programa de Pós- Graduação em Engenharia Elétrica da Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brasil.
- Rezende, T. M.; Castro, C. L.; Almeida, S. G. M. Análise da expressão facial em reconhecimento de sinais de libras. VI Simpósio Brasileiro de Automação Inteligente. Vol. 13. No. 1. 2017.
- Guerra, R. R.; Rezende, T. M.; Guimaraes, F. G.; Almeida, S. G. M. (2018). Facial Expression Analysis in Brazilian Sign Language for Sign Recognition. In Anais do XV Encontro Nacional de Inteligência Artificial e Computacional (pp. 216-227). SBC.