Penggunaan Fitur Saliency-SURF untuk Klasifikasi Citra Sel Darah Putih dengan Metode SVM

Sel darah putih merupakan sel pembentuk komponen darah yang berfungsi melawan berbagai penyakit dari dalam tubuh (sistem kekebalan tubuh). Sel darah putih dibagi menjadi lima jenis, yaitu basofil, eosinofil, neutrofil, limfosit, dan monosit. Pendeteksian jenis sel darah putih dilakukan di laboratorium yang memerlukan seorang spesialis serta usaha yang lebih, waktu, dan biaya. Solusi yang dapat dilakukan salah satunya adalah menggunakan machine learning seperti support vector machine (SVM) dengan ekstraksi fitur SURF. Penelitian ini menggunakan dataset citra sel darah putih yang sebelumnya dilakukan tahap pre-processing yang, terdiri dari crop, resize, dan saliency. Metode saliency mampu memberikan bagian yang bermakna pada sebuah citra. Metode ekstraksi fitur SURF mampu memberikan keypoint yang dapat digunakan SVM dalam mengenali jenis sel darah putih. Penggunaan region-contrast saliency dengan kernel radial basis function (RBF) mendapatkan hasil akurasi, presisi, dan recall yang baik di bandingkan dengan penggunaan kernel lain dalam penelitian ini. Berdasarkan hasil pengujian yang didapat pada penelitian ini, saliency dapat meningkatkan hasil akurasi, presisi, dan recall dari SVM untuk dataset citra sel darah putih dibandingkan dengan tanpa saliency.

Klasifikasi Jenis Buah dan Sayuran Menggunakan SVM Dengan Fitur Saliency-HOG dan Color Moments

Fruit is part of a plant that comes from the flower or pistil of the plant and usually has seeds. Meanwhile, vegetables are leaves, legumes, or seeds that can be cooked. Fruits and vegetables have many variants that can be distinguished based on color, shape, and texture. The Saliency-HOG feature and Color moments were used in this study to extract shapes and colors features in fruit and vegetable images. In this study, the Support Vector Machine (SVM) method was used to classify the types of fruit and vegetables. The dataset used in this study is a public dataset consisting of 114 images of fruit and vegetables. Each type of fruit and vegetable contains 100 images consisting of 70 images as training data and 30 images as testing data. There are 4 saliency features used in the testing phase, namely Region Contrast (RC), Frequency-tuned (FT), Histogram Contrast (HC), and Spectral Residual (SR). Based on the test results, the Saliency-HOG and Color Moments features were able to provide good results with the best precision, recall, and accuracy being 98.57%, 98.55%, and 99.120%, respectively.

Huge Retroperitoneal Dermoid: A Presentation

Teratoma can be defined as a true neoplasm that contains tissues that either are foreign to the primary site of origin or are histologically diverse and represent more than one of the embryonic germ layers. A 20-year-old female patient presented with chief complaints of swelling in the right upper abdomen since childhood and back pain for the past 4 years. Per abdomen, examination revealed a lump of around 15 cm in size in the right hypochondrial region extending to the epigastric region. Contrast-enhanced computed tomography abdomen revealed a 14.3 × 14.1 × 17.4 cm well-defined heterogeneously hypoattenuating nonenhancing complex cystic mass with focal areas of calcifications and fat attenuation in retroperitoneum. The patient was taken up for exploratory laparotomy and a tumor was found in the retroperitoneum, retrocavally and was excised with due care. Histopathological examination features were suggestive of mature cystic teratoma. The postoperative stay was uneventful.