The duplicate finder is great when you don’t know what you’re looking for. It scans a folder and automatically groups everything similar. But what if you already know exactly which file you want copies of?
That’s where Reverse Image Search comes in. Instead of grouping everything, you upload one reference file first. Sakarto processes it immediately, then scans your chosen folder and returns only the files that look like that specific reference. The reference is pinned at the top with a protected badge—it can never be accidentally moved or deleted.
With the Color Signature algorithm, it finds copies based on actual colour distribution—the only algorithm in Sakarto’s toolkit that compares colour instead of just brightness. This makes it uniquely powerful for finding copies that share the same colour palette as your reference, even if they’ve been re-compressed, resized, or saved in different formats.
What makes Color Signature reverse search different from the hash-based algorithms?
All hash-based algorithms—aHash, dHash, pHash, wHash, and BlockHash—convert images to grayscale before processing. They compare brightness structure only and completely ignore colour. Two photos with identical brightness patterns but completely different colours (a bright red car and a bright blue car) would look similar to these algorithms.
Color Signature does the opposite. It keeps colour information front and centre, comparing the actual YUV values across a 24×24 regional grid. YUV is the colour model used in JPEG compression, MPEG video encoding, and television broadcast standards—it separates brightness (Y) from colour information (U and V), which is exactly what you want for accurate colour comparison.
This means Color Signature can distinguish between a bright-red photo and a bright-green photo even if their brightness patterns are identical. It’s the algorithm to use when colour accuracy matters—which, for most photo collections, it does.
How reverse search works
The standard Find Duplicate Images & Videos workflow scans a folder and compares every file against every other file. That’s O(n²) complexity—fine for a few hundred images, but it gets slower as the folder grows.
Reverse Search does something much smarter. It fingerprints your reference once, then compares each folder file only against that reference. That’s O(n) complexity—linear scaling. A folder of 10,000 images takes roughly the same time per file as a folder of 100. The scan speed depends only on the number of files, not how many of them are similar to each other.
This makes reverse search the faster choice for large folders where you already know what you’re looking for.
The reference protection system
The reference file is treated differently from every other file in the scan. When you upload it, Sakarto immediately:
- Computes its colour signature using the Color Signature algorithm
- Shows a thumbnail preview so you can confirm the right file was loaded
- Pins it at the top of the results as soon as scanning starts
- Displays a blue REFERENCE badge on the card
- Prevents it from being moved or deleted—Move and Delete buttons are disabled on the reference card
This last point is critical. If you’re using reverse search to find copies of a file you want to keep, you don’t want to accidentally delete the original. The reference protection system makes that impossible.
How the Color Signature algorithm works
The Color Signature algorithm follows a straightforward pipeline. Here’s exactly what happens when you run a reverse search:
Step 1: Process the reference file immediately
When you upload your reference file, Sakarto processes it right away—before you even select the folder to search. The image is drawn onto a 288×288 canvas, divided into a 24×24 grid, and the average YUV (luminance + chrominance) values are computed for each of the 576 cells. The reference card appears immediately with a blue REFERENCE badge, confirming that your file is loaded and ready.
Step 2: Build the reference fingerprint
For each of the 576 cells, Sakarto computes the average Y, U, and V values. These three channels are normalised independently, making the fingerprint robust to overall brightness adjustments while preserving relative colour differences. This is the “fingerprint” that everything in the folder will be compared against.
Step 3: Process each folder file
For each image or video in the folder, Sakarto draws it onto the same 288×288 canvas and computes its YUV signature using the same 24×24 regional grid. Image processing runs in a background Web Worker via OffscreenCanvas, so the UI stays responsive throughout the scan.
Step 4: Compare against the reference
Every scanned file is compared directly to the reference file’s signature using squared Euclidean distance across all three YUV channels. If the total distance is below the threshold, the file is considered a match. An aspect-ratio pre-check skips files with very different proportions before the full comparison runs.
Step 5: Matches appear live
Each time a matching file is found, its card is added to the results list right away—you see matches accumulate in real time. The header count updates live. When the scan finishes, the final count is shown.
What Color Signature reverse search finds well
| Type of copy | How well it works | Why |
|---|---|---|
| Exact copies of your reference | ✅ Excellent | The colour grid will be identical. |
| Reference saved at different resolutions | ✅ Excellent | The grid is resized to 288×288 first, so resolution differences don’t matter. |
| Re-exported copies in different formats (JPEG → PNG → WebP) | ✅ Excellent | Compression changes pixel values slightly but rarely changes the average colour of a 12×12 cell. |
| Re-compressed social media downloads | ✅ Excellent | Social media platforms apply aggressive JPEG compression, but the colour distribution across regions stays almost identical. |
| Screenshots of the reference image | ✅ Very Good | Screenshots add slight colour shifts but the overall palette remains recognisable. |
| Videos sharing key visual scenes with the reference | ✅ Good | Video frames are extracted and compared as images. The same scene in different codecs will match. |
| Copies with heavy colour grading or filters | ⚠️ May miss | If someone applied a strong colour grade that shifts hues, the U and V values change significantly. |
| Rotated or mirrored versions | ❌ Won’t find | Rotating an image moves all the colour regions—the grid no longer aligns. Use ORB for rotated copies. |
| Heavily cropped versions (over 30% removed) | ❌ Won’t find | Removing a large portion of the frame changes the colour distribution too much. |
| Black-and-white vs. colour versions | ❌ Won’t find | A colour photo and its desaturated version have dramatically different U and V values (both zero for B&W). |
How to interpret the similarity threshold slider
The threshold slider determines how strictly a folder file must match your reference to be considered a copy. Lower values = stricter matching.
| Threshold range | What it does | When to use |
|---|---|---|
| 3–8 (Very strict) | Only near-identical colour signatures match. False positives are very rare. | When you want only exact or near-exact copies of your reference. |
| 10–15 (Balanced) | Catches resized, re-compressed, reformatted, and lightly edited copies. | Default and recommended. Good starting point for most reverse searches. |
| 16–25 (Loose) | Includes more approximate colour matches. More false positives but catches more copies. | If you’re missing copies that look similar but have slightly different colour palettes (e.g. different white balance settings). |
| 25+ (Very loose) | Groups images with broadly similar colour palettes. High false positive rate. | Only use if you’re exploring a folder and don’t mind false positives. Always preview before acting. |
Tip: Start at 10. If you’re missing copies you know exist, raise the threshold. If you’re getting too many false positives, lower it.
How to use Color Signature reverse search: step by step
Step 1: Select your reference file
Click Choose Reference File in the left panel. Select any image or video from your computer. A preview appears immediately so you can confirm you picked the right file. Sakarto processes the reference file right away—computing its colour signature before you even select the folder. This means the search starts instantly once you pick a folder.
Tip: The reference file does not need to be inside the folder you’re about to scan. It can be from anywhere on your computer.
Step 2: Select the folder to search
Once a reference file is loaded, the Choose Folder to Search button becomes active. Click it to open a native folder picker (Chrome/Edge). Or drag and drop a folder onto the page. The folder count shows how many files were found. The Start Search button activates once both the reference file and a folder are selected.
Tip: Enable Fast Mode in the toolbar if you’re scanning many JPEG files—it reads embedded thumbnails and is 5–10× faster than loading full images.
Step 3: Start the search
Click 🔍 Start Search. The reference file card appears immediately at the top of the results with a blue REFERENCE badge. A progress bar shows how many files have been scanned. You can switch browser tabs during the scan—image processing runs in a background Web Worker and continues uninterrupted. Video processing pauses when the tab is hidden and resumes when you return.
Step 4: Review matches as they appear
Every time a matching file is found, it appears as a new card next to the reference. The header count updates live. Once the scan finishes, a final summary shows the total number of similar files found.
- Click a card to select it (blue border)
- Ctrl+Click (Cmd+Click on Mac) to add to the compare list (purple border)
- Click the 🔍 icon on hover to preview full size with metadata
- Right‑click any card for the context menu (the reference card has Move/Delete grayed out)
- Click & drag on empty space to box‑select multiple result cards
Step 5: Compare reference vs. match side‑by‑side
Ctrl+Click the reference card and one or more match cards, then click ⚖️ Compare in the toolbar. A modal opens showing all selected files side‑by‑side with their dimensions, file size, path, and a similarity percentage. For 3+ files, a full pairwise similarity matrix is shown. Similarity percentages above 80% are shown in green, 50–80% in amber, and below 50% in red—giving you a quick visual indicator of how close each match is to your reference.
Step 6: Act on matches—Move, Delete, or Copy
Select the files you want to act on (not the reference—it’s protected) and use the toolbar. With Queue Mode on (recommended), files are staged first:
- 📋 Copy — copy filename(s) to clipboard
- 📂 Move — stage matches for move to a named folder
- 🗑️ Delete — stage matches for permanent deletion
- ⚖️ Compare — view selected files side‑by‑side
Warning: Deletions are permanent. The File System Access API bypasses the recycle bin. Always use Queue Mode to review before executing. The reference file cannot be deleted or moved.
Step 7: Queue Mode—review before you commit
When Queue Mode is enabled (the default), clicking Move or Delete stages files rather than acting immediately. Switch to the Move Queue or Delete Queue tab in the sidebar to review what’s staged, remove individual files, then execute when ready.
Reverse Search vs. Find Duplicates: which to use?
| Reverse Search | Find Duplicates | |
|---|---|---|
| What it does | Finds copies of one specific reference file | Groups all similar files in a folder |
| Complexity | O(n) — each file compared against reference | O(n²) — all files compared against each other |
| Speed | Faster for large folders | Slower for large folders |
| Reference protection | Yes — reference pinned and cannot be deleted | No — all files are treated equally |
| Best for | You know exactly which file you’re looking for | You want to see every duplicate group in a folder |
| When to use | ”I need to find every copy of this specific photo" | "I need to clean up my entire photo library” |
Recommendation: Use both. Run Find Duplicates to see the big picture. Then use Reverse Search for specific important files to clean up their copies without risking the originals.
When to use Color Signature vs. the other 6 algorithms for reverse search
Sakarto gives you seven visual algorithms for a reason—each one handles a different type of duplication problem. Here’s when to pick Color Signature over the others:
aHash (Average Hash) — speed above all else
aHash is the fastest algorithm—it reads individual pixels and compares them to the overall mean.
Use Color Signature instead: Colour accuracy matters. aHash discards colour entirely and would group a blue version and a red version of your reference together—Color Signature keeps them separate.
BlockHash — noise tolerance
BlockHash averages brightness over blocks, making it tolerant of compression noise.
Use Color Signature instead: You want to find colour-similar copies, not just brightness-similar ones. Color Signature gives you colour-aware results that BlockHash can’t provide.
dHash (Difference Hash) — brightness and exposure-adjusted copies
dHash encodes gradient directions and handles exposure shifts well.
Use Color Signature instead: You want to find copies that share the same colour palette as your reference, even if they’ve been re-compressed. dHash ignores colour entirely.
pHash (Perceptual Hash) — format conversions and watermarks
pHash uses the Discrete Cosine Transform to extract low‑frequency structural data—the most precise hash algorithm.
Use Color Signature instead: Colour matters more than structural precision. If your reference has a distinctive colour palette (brand colours, specific lighting, particular filters), Color Signature will find copies based on that palette that pHash would miss.
wHash (Wavelet Hash) — speed and quality balance
wHash uses the Haar Wavelet Transform—similar quality to pHash at lower CPU cost.
Use Color Signature instead: You’re looking for colour-similar copies, not structurally similar ones. wHash ignores colour like all other hash algorithms.
ORB (Feature Matching) — rotation, cropping, and perspective
ORB is the only algorithm that handles rotation, cropping, and perspective distortion.
Use Color Signature instead: Your reference’s copies aren’t rotated or heavily cropped—you just want colour-similar copies. Color Signature is much faster than ORB for this use case.
Color Signature — colour-aware reverse search specialist
Color Signature is the only algorithm that compares actual colour. Use it when colour accuracy matters and you want to find copies that share the same palette—even if they’ve been re-compressed or resized.
Use Color Signature when: Your reference has a distinctive colour palette (brand colours, specific lighting, particular filters). You want to find copies that share that colour palette across different formats, resolutions, and re-compression levels.
Algorithm quick reference for reverse search
| Algorithm | Best for | Colour‑aware? | Handles rotation? | Handles cropping? | Speed |
|---|---|---|---|---|---|
| Color Signature | Same colour palette, social media re‑uploads | ✅ Yes | ❌ No | ❌ No | Fast |
| aHash | Large folders, speed priority | ❌ No | ❌ No | ❌ No | Fastest |
| BlockHash | Heavily compressed JPEGs, noisy images | ❌ No | ❌ No | ❌ No | Very Fast |
| dHash | Brightness/exposure‑adjusted copies | ❌ No | ❌ No | ❌ No | Very Fast |
| pHash | Format conversions, watermarks, precision | ❌ No | ❌ No | ❌ No | Fast |
| wHash | Speed + quality balance | ❌ No | ❌ No | ❌ No | Fast |
| ORB | Rotated, cropped, perspective‑warped | ❌ No | ✅ Yes | ✅ Yes | Slower |
Privacy: your files never leave your device
Like every Sakarto tool, the reverse image search runs entirely in your browser:
- Zero network activity after page load. Open DevTools → Network tab and verify: no outbound requests during any search, compare, or file operation. Your reference file and folder contents are never transmitted anywhere.
- No accounts, no cookies, no analytics. The only localStorage data is your OS detection and checkbox preferences. No file names, paths, or scan results are ever saved.
- Folder access is scoped and session‑only. Permission is granted only for the specific folder you select, lasts only while the tab is open, and is revocable at any time from browser site settings.
- Purely static—no backend. Sakarto is HTML, CSS, and JavaScript. There is no server, no database, and no API receiving any data from you.
Frequently asked questions (Color Signature reverse search specific)
“How is Color Signature reverse search different from aHash, dHash, or pHash reverse search?”
Every hash‑based algorithm (aHash, dHash, pHash, wHash, BlockHash) converts images to grayscale before processing—they compare brightness structure only and completely ignore colour. Color Signature is the only algorithm that compares actual colour. It measures the average YUV value (Y = luminance, U and V = colour channels) across a 24×24 regional grid. Two images with a similar colour palette across their regions will match; two images with the same brightness pattern but different colours won’t. This makes Color Signature uniquely able to find colour‑similar copies of your reference that grayscale algorithms group incorrectly or miss entirely. The trade‑off: colour‑shifted versions of your reference (different white balance, filtered in Instagram, hue‑rotated) won’t match even if the subject is identical.
”Does my reference file need to be inside the folder I’m scanning?”
No—select it from anywhere on your computer. Sakarto automatically skips the reference file if it appears inside the scanned folder, matched by filename, file size, and last‑modified timestamp. The reference card is pinned at position 0 and is never treated as a scan result even if an identical file exists in the folder.
”A copy of my reference isn’t appearing. What should I try?”
First, raise the threshold slider. Second, consider whether the copy has been colour‑graded, filtered, had its white balance changed, or converted to black and white—any of these will shift the YUV values in the 24×24 grid enough to reduce the similarity score. Color Signature is intentionally sensitive to colour changes because that’s its purpose, but it means colour‑processed copies won’t be found. For colour‑insensitive matching, try pHash or dHash. Third, check aspect ratios—pairs differing by more than 10% are excluded. Fourth, for rotated or heavily cropped copies, try ORB.
”I’m seeing too many unrelated images as matches. How do I reduce false positives?”
Lower the threshold slider. At loose thresholds, images that share a similar overall colour palette—two outdoor nature photos both dominated by greens and blues, or two sunny portraits both warm‑toned—can match your reference even if they’re completely different scenes. Tighten the threshold to 3–7 to require a much closer regional colour match. If false positives still occur at strict thresholds with this particular reference, the folder may contain many images with genuinely similar colour palettes. In that case, combine results with a second pass using pHash and keep only files that appear as matches in both.
”Does Color Signature work well for finding re‑compressed versions of my reference downloaded from social media?”
Yes—this is one of its strongest use cases. When an image is downloaded after platform re‑encoding, individual pixel values change slightly but the regional colour distribution across the 24×24 grid stays almost identical. The YUV averages per region are very stable across quality changes. At a threshold of 8–12, Color Signature reliably identifies re‑compressed downloads even from platforms with aggressive compression (WhatsApp, older Twitter, Messenger). For very heavily compressed versions (quality 20 or below), try raising the threshold to 12–18.
”Can Color Signature find video copies of my reference image?”
Yes, and this works both ways—an image reference can match similar video frames, and a video reference is compared against both images and videos in the folder. For videos, Sakarto extracts 3 frames at regular intervals and computes an averaged colour signature. This means a video that contains a scene similar to your reference image will appear as a match. Note that video matching via colour signature is less precise than image matching—two videos sharing a similar colour scene can match even if they have different content. Always preview video matches before acting.
”Why does video scanning pause when I switch tabs?”
Browsers throttle video element processing when a tab is hidden to conserve battery and CPU. Sakarto detects this via the Page Visibility API and pauses video frame extraction automatically, resuming when you return. Image processing runs in a background Web Worker that is not throttled by tab visibility—images keep scanning at full speed regardless of which tab you have open.
”Can I recover files after deleting them?”
No. Sakarto’s remove() call permanently deletes files without going through the OS Recycle Bin or Trash. The reference file is always protected and cannot be deleted. For matched files, always use Queue Mode to stage and review before executing. Moving to a “Sakarto‑Duplicates” subfolder is a safer alternative to immediate deletion.
”Does this work on Firefox or Safari?”
Reference processing, colour comparison, result display, and the Compare modal all work in Firefox and Safari. Move and Delete require the File System Access API (Chrome 86+ and Edge 86+ only). In other browsers, complete the search, review results, and use Download List to export a report for manual file management.
Final thoughts
Color Signature reverse search is the tool you reach for when you have a specific reference image or video and need to find every copy of it across a folder. It’s faster than the duplicate finder for large folders, it protects your reference file, and it finds copies based on actual colour—the only algorithm in Sakarto’s toolkit that does so.
It’s particularly effective for:
- Finding copies of a specific photo. You know exactly which image you’re looking for—use reverse search to find it.
- Tracking brand assets. Use a reference logo or product image and find every version across your archives.
- Cleaning up duplicates of a specific file. Instead of scanning a whole folder, target just the files you know are duplicates of your reference.
- Social media re-uploads. Your reference was re-compressed when uploaded—Color Signature finds the re-downloaded copies.
Where Color Signature falls short—rotated, colour‑shifted, or heavily cropped copies—other Sakarto algorithms fill the gap. Use ORB for rotated or cropped copies, pHash or dHash for colour‑insensitive matching, or aHash for speed.
But for colour‑aware reverse searching, Color Signature is the algorithm that finds the copies the others miss.
Ready to find every copy of your reference image or video by colour?
- Open Color Signature Reverse Search — free, browser‑based, no install
- Try Find Duplicates with Color Signature — auto‑group all similar files without a reference
- Explore All 7 Reverse Image & Video Algorithms — compare with aHash, BlockHash, dHash, pHash, wHash, and ORB