Determinação de curva glicolítica em carcaças de aves PSE (Pale, soft, exsudative) e normal em linha de abate industrial

Some quality defects can cause changes in attributes of the meat, among these we can detach the PSE meat (Pale, Soft and Exudative). The PSE meat is pale, flaccid and exudative and result from sudden pH decrease while the carcass is still under high temperature. The identification of PSE meat has been done by measuring pH and L* (Lightness). However, studies suggest that a more precise evaluation of the kinetics of pH and temperature decrease has to be conducted to better understand the etiology of PSE meat in poultry. The aim of this study was to obtain the glycolytic curve for normal and PSE meat of chicken, through the pH, L* and CRA (water holding capacity) analysis. This experiment was conducted with carcasses obtained from a commercial slaughterhouse (n = 35) of Cobb lineage, 50 days old, from the same batch of creation and with the same pre-slaughter fasting time (10h). Samples of breast fillets were obtained from carcasses randomly collected immediately at the output of pre-cooling chiller, and the analysis of pH, temperature and L * were conducted in the same in times 1h35, 2h35, 3h35, 5h35, 8h35, 11h35, 14h35, 17h35, 20h35, 23h35 and 25h35 post mortem. The CRA analyzes were performed at the time of 25h35 post mortem. The pH measurements indicated that only from the 04 time (8h35 post mortem) was possible to verify an indicative of stabilization, being that PSE meat pH was 5,69±0,07, and normal meat was 5,93±0,09. The final pH (25h35 post mortem) was 5,98±0,06 and L* 57,30± 2,39 for normal meat, while for PSE meat the result was 5,72±0,06 and L* 59,44±1,51. To CRA, the average of the samples (67,19±3.13 and 64,45± 2.66) showed a difference between the normal chicken fillets and PSE respectively. The data found in this study are consistent with those reported by own research group in another slaughterhouse and contradicts similar works, but made at room temperature, indicating that for chickens under commercial conditions the resolution of rigor mortis occurs after 8h35 post mortem.

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.