Recognition of handwritten katakana in a frame using moment invariants based on neural network

1991 ◽  
Author(s):  
Takeshi Agui ◽  
Hiroki Takahashi ◽  
Masayuki Nakajima ◽  
Hiroshi Nagahashi
Keyword(s):  
Neural Network ◽  
Moment Invariants

Orbit Shape Automatic Recognition Based on Artificial Neural Network

2005 ◽  
Author(s):  
Dongmei Du ◽  
Qing He
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fault Diagnosis ◽  
Expert System ◽  
Recognition Performance ◽  
Shape Recognition ◽  
Vibration Monitoring ◽  
Moment Invariants ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Orbit is a significant symptom in the fault diagnosis of rotating machine. The orbit is a 2-D image and can be described by moment invariants, the shape property of 2-D image, which is a description with translating-, rotating-, and scaling-invariants for 2-D image. The descriptive method of orbit image is investigated and an automatic orbit shape recognition based on artificial neural network (ANN) with moment invariants is proposed in this paper. The ANN of orbit shape recognition is trained by the training patterns generated by computer simulation for plenty of orbit shapes. It is shown that the trained ANN is of good recognition performance and generalization capability when applied to recognition of the measured orbits. This method can be used to the intelligent expert system of fault diagnosis to obtain automatically online orbit symptom in shafts vibration monitoring of turbine generator, which will improve the automatization of obtaining fault symptom and the automatic diagnosis in the expert system.

Color Face Recognition Based on Quaternion Zernike Moment Invariants and Quaternion BP Neural Network

2013 ◽  
Vol 446-447 ◽  
pp. 1034-1039 ◽  
Author(s):  
Bei Jing Chen ◽  
Hua Zhong Shu ◽  
Gang Chen ◽  
Jun Ge
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Bp Neural Network ◽  
Recognition Rate ◽  
Zernike Moment ◽  
Moment Invariants ◽  
Intensity Information ◽  
Active Research ◽  
Facial Images ◽  
Color Face Recognition

As an active research topic, many algorithms have been presented for face recognition. However, they mainly utilize the monochromatic intensity information. Among a few color face recognition methods, most of them treat the three channels separately. In this paper, a color face image is treated in a holistic manner by using the quaternion theory. We then propose a new algorithm for color face recognition, which uses the quaternion Zernike moment invariants and the quaternion BP neural network for the color face recognition. Experimental results on the Collection of Facial Images (Grimace) database, including major expression variation and considerable variation in head turn and tilt, show that the proposed method is better than the conventional ones in recognition rate.

scholarly journals Akurasi dalam Mengidentifikasi Citra Anggrek Menggunakan Backpropagation Artificial Neural Network

2021 ◽  
Author(s):  
Ardia Ovidius ◽  
Gunadi Widi Nurcahyo ◽  
Sumijan ◽  
Roni Salambue
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Back Propagation ◽  
Moment Invariants ◽  
Artificial Neural ◽  
Backpropagation Artificial Neural Network

Anggrek merupakan tanaman bunga hias dalam Family Orchidaceae yang habitatnya terdistribusi pada hampir seluruh benua didunia, kecuali benua Antartika.  Di Indonesia sendiri, sangat banyak peminat anggrek sehingga menjadikan bunga ini sebagai komoditas yang cukup menjanjikan bagi penggiat tanaman hias.  Dengan ragam jenis anggrek yang mencapai lebih dari 25.000 spesies, identifikasi jenis anggrek menjadi sedikit rumit bagi para pecinta anggrek.  Tujuan penelitian ini adalah untuk menentukan tingkat akurasi pengidentifikasian jenis anggrek melalui pengenalan gambar, sehingga dapat menjadi acuan dalam menentukan kelayakan metode tersebut.  Penelitian ini menggunakan 120 citra anggrek yang terdiri dari 6 spesies.  Citra anggrek tersebut diperoleh dengan melakukan pemotretan pada beberapa lokasi menggunakan kamera.  Foto tersebut kemudian diolah menggunakan software pengolah citra dengan melakukan cropping dan resizing untuk mempercepat waktu komputasi saat pelatihan jaringan.  Selanjutnya software MatLab digunakan untuk melakukan proses ektraksi ciri berupa data warna dan moment invariants. Data hasil ekstraksi ciri dijadikan input untuk melatih jaringan syaraf tiruan dengan metode Back Propagation.  Penghitungan tingkat akurasinya dengan uji coba menggunakan data uji yang sudah disediakan. Hasil uji coba menunjukkan bahwa 26 dari 30 berhasil dikenali sehingga tingkat akurasi dapat dihitung yaitu 86,7%.  Tingkat akurasi sebesar 86,7% dapat dianggap layak dan bisa dijadikan landasan pertimbangan untuk menggunakan metode yang diuji coba ini sebagai metode yang tepat dalam melakukan identifikasi anggrek melalui citra.

Automatic identification of axis orbit based on both wavelet moment invariants and neural network

2003 ◽  
Vol 8 (2) ◽  
pp. 414-418 ◽  
Author(s):  
Fu Xiang-qian ◽  
Liu Guang-lin ◽  
Jiang Jing ◽  
Li You-ping
Keyword(s):  
Neural Network ◽  
Automatic Identification ◽  
Moment Invariants ◽  
Axis Orbit

scholarly journals NEURAL NETWORK BASED CLASSIFICATION USING BLUR DEGRADATION AND AFFINE DEFORMATION INVARIANT FEATURES

2001 ◽  
Vol 10 (01n02) ◽  
pp. 243-256 ◽  
Author(s):  
YANI ZHANG ◽  
CHANGYUN WEN ◽  
YING ZHANG ◽  
YENG CHAI SOH
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Pattern Analysis ◽  
Moment Invariants ◽  
Normalization Procedure ◽  
Image Normalization ◽  
Invariant Moments ◽  
High Classification Accuracy ◽  
Affine Deformation ◽  
Degraded Images

Identification of affine deformed and simultaneously blur degraded images is an important task in pattern analysis. In this paper, we introduce an image normalization approach to derive blur and affine combined moment invariants (BACIs). In our scheme, the lowest order blur invariant moments are used as the normalization constraints and an appropriate normalization procedure is designed to guarantee that the constraints used in each step should not be affected in the subsequent normalization steps. A neural network (NN) model is then employed to classify the degraded images using the proposed BACIs. Experimental results show that the system has high classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document