aug_jpeg_blocks — 2D augmentation op

• 資料種類:image → image

• 呼叫:fullseye.apply(img, "aug_jpeg_blocks", a=0.5, b=0.5)(2-D 的模型是一張圖 + 兩個純量旋鈕 a,b∈[0,1])

用法

> 該運算子的說明尚無譯文,以下照原文給出。

JPEG blocking / ringing artefacts. The image (scaled to 0..255) is cut

into 8x8 blocks, each transformed with an orthonormal 2-D DCT-II

(`scipy.fft.dctn`), quantised with the STANDARD JPEG Annex-K luminance

table scaled by `(1 + 40*a)/16` (a=0 -> near-lossless, a=1 -> heavy

quantisation), then reconstructed with the inverse DCT. `b` shifts the 8x8

block grid phase by `int(7*b)` px in both axes, i.e. moves where the block

seams fall. Images that are not a multiple of 8 are edge-replicate padded and

cropped back to HxW (so 4x4 inputs are handled).

詳細使用指南

• gallery2d_color_artistic 族使用指南

參考(範例資料・文獻)

• 範例資料目錄(下載 URL / 授權) —— 2-D 用 skimage.data(BSD/公有領域)加合成圖,3-D 給出真實資料源(Stanford/PDS 等)的下載 URL。

• 運算子來歷與參考文獻 —— 該運算子族所依據的研究/方法出處。

• 演算法的正典(作者・年份)與用途見上面的族使用指南。

可執行的範例(實際呼叫該運算子並已驗證的樣例)

• gallery2d_color_artistic — py -3.11 examples/gallery2d_color_artistic.py

• sim2real_and_alife — py -3.11 examples/sim2real_and_alife.py

型別可銜接的下一個運算子(可接受 image 作為輸入)

identity · gaussian · mean_box · bilateral · unsharp · median · min_filter · max_filter

同類別(augmentation)

aug_shot_noise · aug_read_noise · aug_fixed_pattern · aug_motion_blur · aug_vignette · aug_chromatic · aug_rolling_shutter · aug_cutout

*Provenance: ops.py — 2D 運算子登記表。本條目由 tools/opdocs.py md 自動產生(請勿手動編輯)。*

© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.