A contribution to semantic description of images and videos: an application of soft biometrics

Humans have a high ability to extract visual data information acquired by sight. Trought a learning process, which starts at birth and continues throughout life, image interpretation becomes almost instinctively. At a glance, one can easily describe a scene with reasonable precision, naming its main components. Usually, this is done by extracting low-level features such as edges, shapes and textures, and associanting them to high level meanings. In this way, a semantic description of the scene is done. An example of this, is the human capacity to recognize and describe other people physical and behavioral characteristics, or biometrics. Soft-biometrics also represents inherent characteristics of human body and behaviour, but do not allow unique person identification. Computer vision area aims to develop methods capable of performing visual interpretation with performance similar to humans. This thesis aims to propose computer vison methods which allows high level information extraction from images in the form of soft biometrics. This problem is approached in two ways, unsupervised and supervised learning methods. The first seeks to group images via an automatic feature extraction learning , using both convolution techniques, evolutionary computing and clustering. In this approach employed images contains faces and people. Second approach employs convolutional neural networks, which have the ability to operate on raw images, learning both feature extraction and classification processes. Here, images are classified according to gender and clothes, divided into upper and lower parts of human body. First approach, when tested with different image datasets obtained an accuracy of approximately 80% for faces and non-faces and 70% for people and non-person. The second tested using images and videos, obtained an accuracy of about 70% for gender, 80% to the upper clothes and 90% to lower clothes. The results of these case studies, show that proposed methods are promising, allowing the realization of automatic high level information image annotation. This opens possibilities for development of applications in diverse areas such as content-based image and video search and automatica video survaillance, reducing human effort in the task of manual annotation and monitoring.

Programa pró-equidade de gênero e raça da Prefeitura Municipal de Curitiba: estratégia para superar a divisão sexual de trabalho em uma instituição pública?

The objective of this study was to analyze if the pro equity program of gender and race in the PMC, changed the perception of the servants on the conception of sexual division of labor. The sexual division of labor is the concept that allows identifying and understanding the hierarchical relations (principal of hierarchization) based on the attribution of social and economic value most male occupations in relation female, besides that, considerers the female work‟s secondary and her salary supplement to the family income. And the principle of separation identifying the places occupies by man and woman in the institution (productive, reproductive, and domestic work) agreeing with the historical and social construction that associates woman to occupational sectors like “mastertship”, nursering and social assistance, considered an extension of the family functions like taking care and family affections. And the man is associate to engineer, technology information and occupations related to exact science all professions associate to reason, creating a bias of gender in labor relations. To identify possible inequalities of gender in the work ambiance, I have compared the initial basic duration of some careers, the ascension process to higher positions and the salary that both servants and servers in the PMC. Was also investigated the perception of implements and beneficiaries of the program, over the sexual labor division. The methodology used for conduct the investigation was the qualitative research interpretive character using the structured and semi structured interviewed as instruments of data collect. The interview was divided in two groups, to follow: a) implements of pro-equity program of gender and race and b) professors and engineers beneficiaries. The analyzes of documents provided by the Secretaria de Politícas para as Mulheres da Presidência da República and by the PMC complemented the investigative path of this research. Bring as result a perception of beneficiaries servants and implementing on a policy which provides for cultural changes in the institution and in the management of people. It should be noted that the program foresees that in its objectives identify the discriminatory relations of race, sexual orientation, generation and disable person who were not examined in this study. Factor that enables the continuation of the investigation process and is a suggestion for a future research.