The most common approach for fingerprint analysis is using minutiae that identifies corresponding features and evaluates the resemblance between two fingerprint impressions. Although many minutiae point pattern matching algorithms have been proposed, reliable automatic fingerprint verification remains as a challenging problem. Finger print recognition can be done effectively using texture classification approach. Important aspect here is appropriate selection of features that recognize the finger print. We propose an effective combination of features for multi-scale and multi-directional recognition of fingerprints. The features include standard deviation, kurtosis, and skewness . We apply the method by analyzing the finger prints with discrete wavelet transform (DWT) . We used Canberra distance metric for similarity comparison between the texture classes. We trained 30 images and obtained an overall performance up to 96%.

/pdf/finger-print-recognition-using-discrete-wavelet-transform-2dvwl74odt.pdf

Finger print recognition using discrete wavelet transform

Tanda tangan merupakan salah satu biometrik pada karakteristik perilaku yang digunakan untuk mengenali seseorang sebagai sistem identifikasi . Meskipun unik, banyak terjadi kasus tanda tangan yang disalahgunakan dengan cara dipalsukan. Tidak mudah mengenali tanda tangan yang palsu dengan tanda tangan asli. Penelitian ini menerapkan algoritma Learning Vector Quantization, deteksi tepi Sobel, dan ekstraksi fitur Local Binary Pattern untuk mengidentifikasi tanda tangan. Hasil penelitian menunjukkan, jumlah data citra, iterasi, dan learning rate mempengaruhi akurasi dan waktu proses identifikasi. Dari percobaan yang dilakukan pada parameter yang berbeda-beda, akurasi yang didapat adalah 68% pada data latih dan pada data uji sebesar 54,6%. Kata kunci — identifikasi, Learning Vector Quantization, tanda tangan, pengenalan pola

/pdf/pengenalan-tanda-tangan-menggunakan-learning-vector-4yovdx99xr.pdf

Pengenalan Tanda Tangan Menggunakan Learning Vector Quantization dan Ekstraksi Fitur Local Binary Pattern

Di era teknologi yang semakin canggih ini, rata-rata masyarakat sudah mulai beralih dari tanda tangan statik yang menggunakan media kertas ke tanda tangan digital dengan menggunakan media pentablet. Maka dari itu kebutuhan akan proses identifikasi tanda tangan digital secara otomatis dengan menggunakan kecerdasan buatan pun semakin banyak diminati. Metode yang peneliti gunakan dalam pengembangan sistem adalah waterfall model yang terdiri dari 6 tahapan. Metode yang digunakan dalam proses identifikasi ini adalah Jaringan syaraf tiruan dengan algoritma Backpropagation. Proses identifikasi ini melewati beberapa tahapan yaitu dari pre-processing data hingga pengolahan citra, citra RGB diubah menjadi grayscale sampai menjadi citra biner yang kemudian digunakan sebagai data input pada proses pelatihan dan pengujian menggunakan Backpropagation. Citra tanda tangan yang telah melewati pre-processing data ini berjumlah 200 sampel yang berasal dari 10 subjek penelitian. Dari 200 citra tersebut, 180 citra digunakan untuk pelatihan dan 20 citra digunakan untuk pengujian. Hasil pengujian pada saat proses pelatihan adalah 75% training = 88.1%, 15% validation = 60.3%, 15% test adalah 59.5% dan 100% all adalah 79.7% sedangkan pada proses pengujian adalah 65%.

Implementasi Backpropagation untuk Identifikasi Tanda Tangan Digital

Nutrient Content NPK is macro nutrient content that important for the growth of a plant. The measurement of NPK conducted periodically, but the measurement using laboratories test need relatively long time. This Research is conducted to determine the nutrient content of the soil, consisted of nitrogen, phosphor, and calcium (NPK) using digital image processing based on Features from Accelerated Segment Test (FAST) and backpropagation artificial neural network. The data sample in this research taken from the rice field soil in Daerah Istimewa Yogyakarta province where the soil taken at the length of 30 cm to 110 cm with l20 cm interval, and -30° to 30° degree with interval 10°. The model from this measurement system based on texture’s characteristic that extracted using Scale Invariant Feature Transform from soil’s image that already passed pre-processing process. The characteristic result will be the input from the artificial neural network with a variation on parameter’s model. The model tested for the purpose of knowing the influence the distance and degree where the image taken and the influence of parameter’s artificial neural network. The result from the research, is a accurate value of the measurement for each nutrient in the soil, nitrogen (94.86%), phosphor (58.93%) and calcium (63.57%), with the mean 72,46%. The corresponding result obtained from image taken with optimal height of 70 cm and degree 0o

/pdf/methods-for-determining-nitrogen-phosphorus-and-potassium-5687lysouf.pdf

Methods for Determining Nitrogen, Phosphorus, and Potassium (NPK) Nutrient Content Using Features from Accelerated Segment Test (FAST)

Identifikasi tanda tangan statik menggunakan jaringan syaraf tiruan backpropagation dan wavelet haar

A rapid development of image processing technique has been currently taking place Image analysis is becoming an application which attracts a lot of attention among the other applications It extracts image features to identify an objectImage analysis has been widely used in several fields such as animal husbandryThe object used in this study is the image of sow vagina Determining the pig breeding time is something necessary for the breeders since it will greatly affect the number of piglets The complexity in determining the pig breeding period becomes a main problem in this research This system has been successfully established The system can recognize patterns well with a maximum recognition rate of 987013% In general Haar wavelets, db2 and coif1 produce better recognition performance Haar wavelets are wavelets that have fewer computational loads than others

/pdf/determining-pigs-breeding-time-by-sow-s-vagina-image-10aicc08j7.pdf

Ernawati

Papers

Identifikasi tanda tangan statik menggunakan jaringan syaraf tiruan backpropagation dan wavelet haar

Determining Pigs Breeding Time by Sow's Vagina Image Analysis Using Wavelet Transforms and Artificial Neural Network