Feature Extraction and Machine Learning for the Classification of Brazilian Savannah Pollen Grains.

The classification of pollen species and types is an important task in many areas like forensic palynology, archaeological palynology and melissopalynology. This paper presents the first annotated image dataset for the Brazilian Savannah pollen types that can be used to train and test computer vision based automatic pollen classifiers. A first baseline human and computer performance for this dataset has been established using 805 pollen images of 23 pollen types.

Evaluation of the effect of collagen network degradation on the frictional characteristics of articular cartilage using a simultaneous analysis of the contact condition.

Background: Superficial conditions and integrity of collagen network play an important role on the lubrication performance of articular cartilage. In this work, a technique based on the evanescent waves is used for the evaluation of contact condition during friction tests.

Methods: The frictional and superficial characteristics of the normal and degraded articular cartilages with high and low concentration of collagenase were evaluated.

Evaluation of the superficial characteristics of articular cartilage using evanescent waves in the friction tests with intermittent sliding and loading.

Articular cartilage plays an important role in the lubrication of synovial joints because of its peculiar characteristics. In this work, the frictional and superficial characteristics of articular cartilage were evaluated simultaneously during intermittent sliding and loading. The apparatus used for the analysis of the articular surface was based on the evanescent waves, where a laser light was reflected at the interface between a prism and a specimen of articular cartilage.