Sign language recognition is a highly-complex problem due to the amount of static and dynamic gestures needed to represent such language, especially when it changes from country to country. This article focuses on static recognition of vowels in Colombian Sign Language. A total of 151 images were acquired for each class, and an additional non-vowel class with different scenes was also considered. The object of interest was cut out of the rest of the scene in the captured image by using color information. Subsequently, features were extracted to describe the gesture that corresponds to a vowel or to the class that does not match any vowel. Next, four sets of features were selected. The first one contained all of them; from it, three new sets were generated. The second one was extracted from a subset of features given by the Principal Component Analysis (PCA) algorithm. The third set was obtained by Sequential Feature Selection (SFS) with the FISHER measure. The last set was completed with SFS based on the performance of the K-Nearest Neighbor (KNN) algorithm. Finally, multiple classifiers were tested on each set by cross-validation. Most of the classifiers achieved a performance over 90%, which led to conclude that the proposed method allows an appropriate class distinction.
Principal Component Analysis; Classification; Combian sign language; Feature selection; Cross-validation.