02056nam a2200253 i 4500003000500000005001700005008004100022040002500063100003300088245013800121300001600259336002100275337002500296338002300321502009500344504003900439520110100478700003201579700003601611720003801647720004801685720003101733720003801764CSPC20250814154043.0250814s2023    ph a     b    000 0 eng d  aCSPCbengcCSPCerda1 aMagistrado, Kyle L.eauthor.10aDisease detection among the napa and cannonball cabbage using cnn /cKyle L. Magistrado, Nerielyn T. Pablo, and Sherah May P. Serrano  a150 leaves.  2rdacontentatext  2rdamediaaunmediated  2rdacarrieravolume  aUndergraduate Thesis (BSCS) - Computer Science.cCamarines Sur Polytechnic Colleges, 2023.  aIncludes bibliographic references.3 aAchieving sustained agricultural yield and global food security in agriculture required effective plant disease identification. This study focused on detecting common illnesses that affect cabbage plants, an essential green vegetable in the Philippines. Nevertheless, the increasing occurrences of plant diseases globally pose a significant threat to food secu-rity. CNN models were used to identify four common diseases that affect two commonly grown cabbage varieties in the Philippines: Napa (Chinese Pechay) and Cannonball cab-bage. This paper used deep CNN architectures, specifically ResNet-34 and VGG16, to distinguish between diseased and healthy leaves. The effectiveness of both algorithms in precisely recognizing and categorizing impacted cabbage leaves was examined. The ResNet-34 achieved a 97.03% model accuracy while the VGG16 achieved an accuracy of 97.86%. These models had the potential to transform plant disease detection by providing accurate and efficient disease identification, protecting crop yields and global food security in the face of changing agricultural problems1 aPablo, Nerielyn T.eauthor.1 aSerrano, Sherah May P.eauthor.  aFortuno, Kaela Marie N.eadviser.  aOñate, Joseph Jessie S.echair, panelist.  aOnesa, Rosel O.epanelist.  aPandes, Tiffany Lyn O.epanelist.