This paper presents a pollination based optimization (PBO) algorithm. PBO is a bio-inspired, multipopulation global optimization algorithm capable of generating high accuracy solutions to complex problems. The plants have been observed to optimize their resource expenditure on fragrance, floral display, nectar production and pollen to attract pollinating agents such as insects, bees, flies, bats, birds, etc. Subject to pollination success, plants increase or decrease their total resource cost on fragrance, superior nectar content, pollen and floral display. If the reproductive success is better, plants decrease their investment. In case the reproductive success is below average, plants increase their investment on resources affecting pollination. This increases the number of pollinators and their re-visitation causing the reproductive success to go up. The proposed PBO algorithm was evaluated on the 80 test functions of CEC 2021 test suite, and the performance was compared with 8 recent algorithms. The algorithm performed exceptionally well, leading in 41 of the 80 functions of the test bench. The paper further, demonstrates the application of the proposed algorithm to evolve an optimized CNN architecture for the paddy plant disease detection from the paddy leaf dataset. The paddy leaf dataset has 5932 infected images indicating various diseases. The PBO based approach with 99.37% accuracy outperformed KNN, SVM, Decision Tree, Random Forest, GA-CNN and BBBC-CNN based algorithms.