TF Image Classifier is a free Chrome extension that runs TensorFlow.js MobileNet v2 and COCO-SSD models locally in your browser to label images and detect objects on any website.
編集部による 5 点満点の評価です。ユーザー評価の平均ではありません。 このページの各視点は、製品情報をもとに AI がまとめたものです。実際の利用者のレビューではありません。
OpenAITools.app のテレメトリ（2026-11-11 検証）によると、TF Image Classifier（chromewebstore.google.com）は AI 画像認識に分類される AI プラットフォームで、月間 0 の訪問を生み出し、前月比のトラフィック増減は +0（0.0%）です。主要な地域市場はグローバル（トラフィックシェア —）で、無料の料金モデルで運営されています。月間ボリューム別の主な競合代替ツールには Ultralytics（月間 79.34万訪問）、Pl@ntNet（月間 43.99万訪問）、T-Rex Label（月間 9900 訪問）が含まれます。
ブラウザ内でローカルにモデルが動くのが面白い。
マニアックな物体は認識ミスが多い。
サイト検証・料金体系・同カテゴリ比較に基づき AI が多角的な論点を要約した参考視点であり、実在ユーザーの個別投稿ではありません。
Labels images across more than 1,000 categories using the TensorFlow.js MobileNet v2 model, giving a broad read on what an image most likely depicts.
Detects and localizes around 80 common object classes with bounding boxes, useful for spotting people, animals, vehicles, and household items in a photo.
Inference happens locally in the Chrome tab through TensorFlow.js, so no image is uploaded to a remote server and no account is needed.
Point it at images on virtually any web page; the developer recommends pairing it with a CORS unblocking extension for images served from other domains.
Built primarily as a hands-on way to explore pre-trained computer-vision models, offered at no cost by an independent developer.
TF Image Classifier is a free Chrome extension that runs TensorFlow.js MobileNet v2 and COCO-SSD models locally in your browser to label images and detect objects on any website.
Experiment with MobileNet and COCO-SSD predictions on real images to build intuition for how computer vision models classify and detect objects.
Get an instant best-guess label for an unknown picture you encounter on the web without leaving the page or uploading anything.
Use the extension as a lightweight reference for what TensorFlow.js models can do in a browser extension context before building your own tooling.
同じ主要カテゴリの競合 AI ツールをテレメトリで並列比較
| 順位 | AI ツール | 月間訪問数 | 前月比成長率 | 直接流入の割合 | 料金 | 直接比較 |
|---|---|---|---|---|---|---|
| ● | TF Image Classifier | 0 | — | — | 無料 | 表示中 |
| 1 | Ultralytics | 79.34万 | +8.7% | 直接流入 30% | フリーミアム | vs Ultralytics |
| 2 | Pl@ntNet | 43.99万 | +34.9% | 直接流入 47% | 無料 | vs Pl@ntNet |
| 3 | T-Rex Label | 9900 | +37.6% | 直接流入 39% | 無料 | vs T-Rex Label |
| 4 | CanIRun.ai | 28.49万 | -20.1% | 直接流入 48% | 無料 | vs CanIRun.ai |
| 5 | NopeCHA | 5.33万 | -14.8% | 直接流入 50% | フリーミアム、有料 | vs NopeCHA |
| 6 | hektCaptcha：hCaptcha ソルバー | 0 | — | — | 無料 | vs hektCaptcha：hCaptcha ソルバー |
無料・オープンソースリアルタイム視覚AIモデルと、その学習・アノテーション・配備を担う統合プラットフォーム
ブラウザだけで使えるAIデータラベリング、1つのプロンプトで画像を一括注釈
自分のGPUやMacで実際に動くローカルAIモデルを確認
ブラウザと自動化パイプラインのためのAI CAPTCHA認識
無料・オープンソースブラウザ内だけで動作する無料・オープンソースの hCaptcha ソルバー
無料のノーコード機械学習モデルトレーニング
OCR - Image Reader is a Chrome extension from developer brian.girko that adds a toolbar button for on-the-fly optical character recognition. Press the button, drag a selection over any region of the active window, and the extension reads the text inside it using a Tesseract-based engine that supports over 100 languages with automatic orientation and script detection. A second engine option, IBM Granite-Docling, goes further and preserves headings, lists, bold and italic styles, tables and even mathematical equations instead of returning flat text. Everything runs offline in the browser, with no server round trips apart from a one-time download of the language training data.
OCR - Image Reader is a Chrome extension from developer brian.girko that adds a toolbar button for on-the-fly optical character recognition. Press the button, drag a selection over any region of the active window, and the extension reads the text inside it using a Tesseract-based engine that supports over 100 languages with automatic orientation and script detection. A second engine option, IBM Granite-Docling, goes further and preserves headings, lists, bold and italic styles, tables and even mathematical equations instead of returning flat text. Everything runs offline in the browser, with no server round trips apart from a one-time download of the language training data.
無料・オープンソースModelScope (魔搭社区) is an open-source AI community and model service platform that hosts thousands of pretrained models, datasets, and ready-to-run demos, backed by Alibaba Cloud infrastructure.
無料・オープンソースModelScope (魔搭社区) is an open-source AI community and model service platform that hosts thousands of pretrained models, datasets, and ready-to-run demos, backed by Alibaba Cloud infrastructure.
無料・オープンソースLocalMode UI is an open-source shadcn registry of copy-owned, composable AI interface components plus installable blocks that run real models directly in the browser. It ships 100+ React components and 36 blocks covering chat, RAG knowledge bases, vision, audio, photo editing, agents and privacy tooling, all designed to be local-first by default and cloud-compatible when you want it.
無料・オープンソースLocalMode UI is an open-source shadcn registry of copy-owned, composable AI interface components plus installable blocks that run real models directly in the browser. It ships 100+ React components and 36 blocks covering chat, RAG knowledge bases, vision, audio, photo editing, agents and privacy tooling, all designed to be local-first by default and cloud-compatible when you want it.
