Using structural and color features of streptomyces clavuligerus bacteria in approximating of production level of clavulanic acid

Nowadays the Production level of Clavulanic Acid from Streptomyces Clavuligerus, as one of the most significant antibiotic compositions, is of specific importance. In this paper Instead of a tentative evaluation of production level, we present an automatic algorithm through the use of the extracted features of bacterial growth in different mediums including carbonic resources such as glycerol, malt, starch, and wheat flour. In this algorithm, by defining special structural and color features such as the number of new branches, hyphal thickness and color receptiveness, bacterial compactness, and also the PH rate of the medium according to microbiologists' discoveries and observations, the estimated value of clavulanic acid is calculated and compared with that of an experienced observation and is evaluated thereafter. In the proposed structure, we utilize a classifier, or in other words an estimator, based on the Perceptron Neural Network, and finally we clarify the efficiency of the proposed algorithm for specialists' utilization.