robin/Dramlog-Prod
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: optimize scan OCR with sharp preprocessing and 1024px resizing

Browse Source
This commit is contained in:
robin
2025-12-24 00:02:58 +01:00
parent 11275dd875
commit a1a91795d1
1 changed files with 16 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
src/app/actions/scan-label.ts
View File

@@ -6,6 +6,7 @@ import { createClient } from '@/lib/supabase/server';
import { createHash } from 'crypto';
import { trackApiUsage } from '@/services/track-api-usage';
import { checkCreditBalance, deductCredits } from '@/services/credit-service';
import sharp from 'sharp';
// Native Schema Definition for Gemini API
const metadataSchema = {
@@ -100,14 +101,23 @@ export async function scanLabel(input: any): Promise<AnalysisResponse> {
};
}
// Step 3: Base64 Encoding
// Step 3: AI-Specific Image Optimization (Grayscale, Normalize, Resize)
const startOptimization = performance.now();
const optimizedBuffer = await sharp(buffer)
.resize(1024, 1024, { fit: 'inside', withoutEnlargement: true })
.grayscale()
.normalize()
.toBuffer();
const endOptimization = performance.now();
// Step 4: Base64 Encoding
const startEncoding = performance.now();
const base64Data = buffer.toString('base64');
const mimeType = file.type || 'image/webp';
const uploadSize = buffer.length;
const base64Data = optimizedBuffer.toString('base64');
const mimeType = 'image/webp';
const uploadSize = optimizedBuffer.length;
const endEncoding = performance.now();
// Step 4: Model Initialization & Step 5: API Call
// Step 5: Model Initialization & Step 6: API Call
const startAiTotal = performance.now();
let jsonData;
let validatedData;
@@ -164,6 +174,7 @@ export async function scanLabel(input: any): Promise<AnalysisResponse> {
data: validatedData,
perf: {
imagePrep: endImagePrep - startImagePrep,
optimization: endOptimization - startOptimization,
cacheCheck: endCacheCheck - startCacheCheck,
encoding: endEncoding - startEncoding,
modelInit: endModelInit - startModelInit,