Huruf tulisan tangan

Salah satu penerapan computer vision yang sangat menarik dalam solusi dunia nyata adalah melakukan Optical Character Recognition (OCR) untuk membedakan karakter teks tercetak atau tulisan tangan di dalam citra digital dari dokumen fisik.

Mari kita coba memperjelas definisi huruf tulisan tangan ini agar lebih mudah diklasifikasikan.

Seperti yang dapat kita lihat, ini adalah huruf R, sudah biner, dengan sedikit derau. Citra ini sudah dimuat sebagai upper_r_image.

Terapkan operasi morfologi yang akan membuang piksel di dekat batas huruf.

Latihan ini adalah bagian dari kursus

Pemrosesan Citra dengan Python

Petunjuk latihan

Impor modul dari scikit-image.
Terapkan operasi morfologi untuk mengikis (erosi) batas wilayah piksel foreground.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

# Import the morphology module
from ____

# Obtain the eroded shape 
eroded_image_shape = ____.____(____) 

# See results
show_image(upper_r_image, 'Original')
show_image(eroded_image_shape, 'Eroded image')

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Pemrosesan Citra dengan Python

SkillTag.level.intermediateSkillTag.label

4.8+

Mulai Kursus Gratis

Jump into digital image structures and learn to process them! Extract data, transform and analyze images using NumPy and Scikit-image. With just a few lines of code, you will convert RGB images to grayscale, get data from them, obtain histograms containing very useful information, and separate objects from the background!

Exercise 1: Make images come alive with scikit-image Exercise 2: Is this gray or full of color?Exercise 3: RGB to grayscale Exercise 4: NumPy for images Exercise 5: Flipping out Exercise 6: Histograms Exercise 7: Getting started with thresholding Exercise 8: Apply global thresholding Exercise 9: When the background isn't that obvious Exercise 10: Trying other methods Exercise 11: Apply thresholding

You will learn to <strong>detect object shapes</strong> using edge detection filters, <strong>improve medical images</strong> with contrast enhancement <strong>and even enlarge pictures to five times its original size! </strong> You will also apply morphology to make thresholding more accurate when segmenting images and go to the next level of processing images with Python.

Exercise 1: Mulai dengan penyaringan Exercise 2: Deteksi tepi Exercise 3: Mengaburkan untuk mengurangi derau Exercise 4: Peningkatan kontras Exercise 5: Berapakah kontras gambar ini?Exercise 6: Citra medis Exercise 7: Citra udara Exercise 8: Mari tambahkan efek dan kontras Exercise 9: Transformasi Exercise 10: Aliasing, rotasi, dan penskalaan ulang Exercise 11: Memperbesar gambar Exercise 12: Mengubah ukuran secara proporsional Exercise 13: Morfologi Exercise 14: Huruf tulisan tangan

Latihan Saat Ini

Exercise 15: Meningkatkan citra hasil threshold

So far, you have done some very cool things with your image processing skills! In this chapter, you will apply <strong>image restoration to remove objects, logos, text, or damaged areas</strong> in pictures! You will also learn how to apply noise, use segmentation to speed up processing, and find elements in images by their contours.

Exercise 1: Image restoration Exercise 2: Let's restore a damaged image Exercise 3: Removing logos Exercise 4: Noise Exercise 5: Let's make some noise!Exercise 6: Reducing noise Exercise 7: Reducing noise while preserving edges Exercise 8: Superpixels & segmentation Exercise 9: Number of pixels Exercise 10: Superpixel segmentation Exercise 11: Finding contours Exercise 12: Contouring shapes Exercise 13: Find contours of an image that is not binary Exercise 14: Count the dots in a dice's image

After completing this chapter, you will have a deeper knowledge of image processing as you will be able to <strong>detect edges, corners, and even faces! </strong> You will learn how to detect not just front faces but also face profiles, cat, or dogs. You will apply your skills to more complex <strong>real-world applications.</strong> Learn to master several widely used image processing techniques with very few lines of code!

Exercise 1: Finding the edges with Canny Exercise 2: Edges Exercise 3: Less edgy Exercise 4: Right around the corner Exercise 5: Perspective Exercise 6: Less corners Exercise 7: Face detection Exercise 8: Is someone there?Exercise 9: Multiple faces Exercise 10: Segmentation and face detection Exercise 11: Real-world applications Exercise 12: Privacy protection Exercise 13: Help Sally restore her graduation photo Exercise 14: Amazing work!