Machine Vision Based Classification of Rice (Oryza Sativa L.) Cultivars Using Morphological, Chromatic and Textural Features of Seed Images

Abstract

Variety identification is an important task for plant breeders, farmers and traders. DUS (Distinctness, Uniformity, Stability) protocol is generally carried out for identification of plant variety which is time consuming and laborious. An attempt was made to quantify 28 rice varieties based on seed images by digital image analysis. Rice seed images were captured using Canon-LiDE110 flatbed scanner at 600 dpi resolutions. An algorithm was developed using Matlab 2012B to capture and extract seven morphological, 18 textural features and seven chromatic features. Discriminant analysis was carried out to identify critical parameters and classified them into similar groups. The study identified 14 best features out of 32 features that has capability to discriminate between rice cultivars. Eccentricity, awn length, major axis, equivalent diameter, kernel area, kernel perimeter and minor axis were found to be most critical among morphological features while standard deviation (STD) and Energy were found to be most critical among textural features while Hue, Red and Green were found to be most critical among chromatic features. Thus the present study indicated that morphological, chromatic as well as textural features play a vital role in identification of new varieties and distinguishing them to classify into similar groups.

Identifikacija vrste je važna za odgajivače, farmere i trgovce. DUS (Rastojanja, Ujednačenost, Stabilnost) protokol je generalno izveden za identifikaciju biljne vrste koja zahteva mnogo vremena i rada. Pokušali smo da kvantifikujemo 28 sorti pirinča na osnovu slika semena digitalnom analizom slike. Semena pirinča su snimljena skenerom Canon-LiDE110 u rezoluciji 600 dpi. Razvijen je algoritam upotrebom Matlab 2012B za hvatanje i izvođenje 7 morfoloških, 18 teksturalnih i 7 hromatskih osobina. Diskriminaciona analiza je izvedena radi identifikacije kritičnih parametara i njihove klasifikacije u slične grupe. Studija je identifikovala 14 najboljih od 32 osobine koje imaju mogućnost razlikovanja sorti pirinča. Ekscentričnost, dužina pleve, glavna osa, ekvivalentni prečnik, površina zrna, obim zrna i mala osa su definisane kao kritične među morfološkim osobinama dok su standardna devijacija i energija izdvojene kao najkritičnije među osobinama teksture. Crvena i zelena boja su bile najkritičnije među hromatskim osobinama. Tako je ova studija pokazala da morfološke, hromatske i osobine teksture igraju odlučujuću ulogu u identifikaciji novih sorti i mkihovog razlikovanja radi klasifikacije u slične grupe.